Unified decoder-only transformers have shown promise for multimodal generation, yet the mechanisms by which they synchronize modalities with heterogeneous sampling rates remain underexplored. We investigate these mechanisms through video-text-to-speech (VTTS) synthesis-a controlled task requiring fine-grained temporal alignment between sparse text, video, and continuous speech. Using a unified decoder-only transformer, dubbed Visatronic, trained on VoxCeleb2, we study: (i) how modalities contribute complementary information, (ii) how positional encoding strategies enable synchronization across heterogeneous rates, (iii) how modality ordering shapes the trade-off between in-domain performance and cross-domain transfer, (iv) how phoneme-level synchronization metrics provide diagnostic insight into per-phoneme timing errors. Our findings reveal that both "global sequential indexing'' (unique position IDs across modalities) and "co-temporal ordered indexing'' (identical IDs for temporally corresponding tokens) achieve strong synchronization performance, with co-temporal ordered indexing providing a simple mechanism without explicit timestamp metadata. Both text and video contribute complementary signals: text ensures intelligibility while video provides temporal cues and emotional expressiveness. Modality ordering reveals a consistent trade-off: video-first ordering achieves stronger in-domain performance while text-first ordering generalizes more robustly to unseen domains. Our findings also reveal, that diverse large-scale training enables transferable synchronization strategies. To enable fine-grained analysis, we also introduce TimeSync, a phoneme-level metric that reveals temporal misalignments overlooked by frame-level metrics. These insights establish VTTS as a valuable testbed for understanding temporal synchronization in unified multimodal decoders.

Large Language Models (LLMs) show promise in lyric-to-melody generation, but models trained with Supervised Fine-Tuning (SFT) often produce musically implausible melodies with issues like poor rhythm and unsuitable vocal ranges, a phenomenon we term "constraint violation". To address this, we propose a novel alignment framework that instills musical knowledge without human annotation. We define rule-based musical constraints to automatically generate a preference dataset from an SFT model's outputs. The model is then aligned through a sequential process, first using Direct Preference Optimization (DPO) on paired preference data, followed by Kahneman-Tversky Optimization (KTO) on unpaired negative samples. Experimental results demonstrate that our aligned model substantially reduces rule violations and outperforms strong baselines in both objective and subjective evaluations, generating melodies with substantially improved musicality and coherence. An interactive demo with audio comparisons is available at https://arain233.github.io/AligningMelody-demo.

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely either on supervised chain-of-thought (CoT) fine-tuning, which is limited by training data quality, or on reinforcement learning (RL) with coarse rewards that do not directly evaluate reasoning quality. As a result, the generated reasoning chains often appear well-structured yet lack specific acoustic grounding. We propose Audio-DeepThinker, a framework built on two core ideas. First, we introduce a hybrid reasoning similarity reward that directly supervises the quality of generated reasoning chains by combining an LLM evaluator assessing logical path alignment, key step coverage, and analytical depth with an embedding similarity component enforcing semantic alignment with reference reasoning chains. Second, we propose a progressive two-stage curriculum that enables high-quality CoT reasoning to emerge through pure RL exploration, without any supervised reasoning fine-tuning, from an instruction-tuned model that possesses no prior chain-of-thought capability. Stage 1 trains on foundational audio QA with the hybrid reward to foster basic reasoning patterns, while Stage 2 shifts to acoustically challenging boundary cases with an LLM-only reward for greater reasoning diversity. Audio-DeepThinker achieves state-of-the-art results on MMAR (74.0%), MMAU-test-mini (78.5%), and MMSU (77.26%), winning 1st Place in the Interspeech 2026 Audio Reasoning Challenge (Single Model Track). Interpretability analyses further reveal that RL training primarily reshapes upper-layer MoE gating mechanisms and that reasoning tokens crystallize progressively in the upper transformer layers, offering mechanistic insights into how audio reasoning emerges through exploration.

We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical patterns by timescale. By masking latents in the frequency domain during training, our method yields representations that can be manipulated coherently at inference. This allows us to generate musical variations and blends from reference examples while preserving characteristics at desired timescales, which are specified as frequencies in the latent space. LatentFT parallels the role of the equalizer in music production: while traditional equalizers operates on audible frequencies to shape timbre, LatentFT operates on latent-space frequencies to shape musical structure. Experiments and listening tests show that LatentFT improves condition adherence and quality compared to baselines. We also present a technique for hearing frequencies in the latent space in isolation, and show different musical attributes reside in different regions of the latent spectrum. Our results show how frequency-domain control in latent space provides an intuitive, continuous frequency axis for conditioning and blending, advancing us toward more interpretable and interactive generative music models.

Instruction-following text-to-speech (TTS) has emerged as an important capability for controllable and expressive speech generation, yet its evaluation remains underdeveloped due to limited benchmark coverage, weak diagnostic granularity, and insufficient multilingual support. We present \textbf{MINT-Bench}, a comprehensive multilingual benchmark for instruction-following TTS. MINT-Bench is built upon a hierarchical multi-axis taxonomy, a scalable multi-stage data construction pipeline, and a hierarchical hybrid evaluation protocol that jointly assesses content consistency, instruction following, and perceptual quality. Experiments across ten languages show that current systems remain far from solved: frontier commercial systems lead overall, while leading open-source models become highly competitive and can even outperform commercial counterparts in localized settings such as Chinese. The benchmark further reveals that harder compositional and paralinguistic controls remain major bottlenecks for current systems. We release MINT-Bench together with the data construction and evaluation toolkit to support future research on controllable, multilingual, and diagnostically grounded TTS evaluation. The leaderboard and demo are available at https://longwaytog0.github.io/MINT-Bench/

Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction. This mismatch injects acoustically driven uncertainty into the discrete token space and increases language-model perplexity. We propose \ours, which augments codec training with language-model-facing objectives while keeping both codec and LLM architectures unchanged. \ours introduces (i) future token prediction with Medusa-style multi-step heads to encourage multi-step predictability, and (ii) semantic alignment that matches audio and text representations via a memory-bank contrastive loss. A differentiable Gumbel bridge enables end-to-end gradients from these objectives to the codec encoder. On SALMon speech coherence, token LMs trained on \ours reach 61.6% accuracy (+12.1 points over AUV) while reducing perplexity 35. On Codec-SUPERB-tiny, \ours improves speech Mel distance by 5.0% over AUV while simultaneously achieving the learnability gains, demonstrating that reconstruction fidelity and token predictability can be improved together.

We present ArtifactNet, a lightweight framework that detects AI-generated music by reframing the problem as forensic physics -- extracting and analyzing the physical artifacts that neural audio codecs inevitably imprint on generated audio. A bounded-mask UNet (ArtifactUNet, 3.6M parameters) extracts codec residuals from magnitude spectrograms, which are then decomposed via HPSS into 7-channel forensic features for classification by a compact CNN (0.4M parameters; 4.0M total). We introduce ArtifactBench, a multi-generator evaluation benchmark comprising 6,183 tracks (4,383 AI from 22 generators and 1,800 real from 6 diverse sources). Each track is tagged with bench_origin for fair zero-shot evaluation. On the unseen test partition (n=2,263), ArtifactNet achieves F1 = 0.9829 with FPR = 1.49%, compared to CLAM (F1 = 0.7576, FPR = 69.26%) and SpecTTTra (F1 = 0.7713, FPR = 19.43%) evaluated under identical conditions with published checkpoints. Codec-aware training (4-way WAV/MP3/AAC/Opus augmentation) further reduces cross-codec probability drift by 83% (Delta = 0.95 -> 0.16), resolving the primary codec-invariance failure mode. These results establish forensic physics -- direct extraction of codec-level artifacts -- as a more generalizable and parameter-efficient paradigm for AI music detection than representation learning, using 49x fewer parameters than CLAM and 4.8x fewer than SpecTTTra.

As speech language models (SLMs) transition from personal devices into shared, multi-user environments, their responses must account for far more than the words alone. Who is speaking, how they sound, and where the conversation takes place can each turn an otherwise benign request into one that is unsafe, unfair, or privacy-violating. Existing benchmarks, however, largely focus on basic audio comprehension, study individual risks in isolation, or conflate content that is inherently harmful with content that only becomes problematic due to its acoustic context. We introduce VoxSafeBench, among the first benchmarks to jointly evaluate social alignment in SLMs across three dimensions: safety, fairness, and privacy. VoxSafeBench adopts a Two-Tier design: Tier1 evaluates content-centric risks using matched text and audio inputs, while Tier2 targets audio-conditioned risks in which the transcript is benign but the appropriate response hinges on the speaker, paralinguistic cues, or the surrounding environment. To validate Tier2, we include intermediate perception probes and confirm that frontier SLMs can successfully detect these acoustic cues yet still fail to act on them appropriately. Across 22 tasks with bilingual coverage, we find that safeguards appearing robust on text often degrade in speech: safety awareness drops for speaker- and scene-conditioned risks, fairness erodes when demographic differences are conveyed vocally, and privacy protections falter when contextual cues arrive acoustically. Together, these results expose a pervasive speech grounding gap: current SLMs frequently recognize the relevant social norm in text but fail to apply it when the decisive cue must be grounded in speech. Code and data are publicly available at: https://amphionteam.github.io/VoxSafeBench_demopage/

Prompt tuning has achieved remarkable progress in vision-language models (VLMs) and is recently being adopted for audio-language models (ALMs). However, its generalization ability in ALMs remains largely underexplored. We observe that conventional prompt tuning for ALMs also suffers from the Base-New Tradeoff, and we identify that this issue stems from the disrupted semantic structure of the embedding space. To address this issue, we propose Semantically Expanded Prompt Tuning (SEPT)-a plug-and-play framework that explicitly regularizes the prompt embedding space by incorporating semantic neighbors generated by large language models. SEPT introduces a novel semantic expansion loss with margin constraints that promote intra-class compactness and inter-class separability, thereby enhancing the semantic structure of the prompt embedding space. For comprehensive evaluation, we establish the first benchmark setup for prompt generalization in ALMs, covering both base-to-new generalization and cross-dataset transferability. Extensive experiments demonstrate that SEPT consistently improves generalization performance across multiple prompt tuning baselines, while maintaining computational cost during inference.

While Audio Large Models (ALMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics -- or ``Acoustic Ecology'' -- that characterize authentic physical environments. To bridge this ecological gap, we introduce \textbf{RSA-Bench}, a comprehensive robustness benchmark designed to stress-test ALLMs through high-fidelity auditory scene simulations. Unlike traditional methods, we construct evaluation samples by naturally superimposing diverse environmental soundscapes -- spanning \textit{Pasture}, \textit{Extreme Weather}, \textit{Classroom}, and \textit{Outdoors} -- onto clean speech signals across a spectrum of interference intensities. By evaluating models on six core tasks ranging from fundamental perception to complex reasoning, our study unveils three macro-level insights: \textbf{(I) The Perception-Cognition Gap:} Models maintain relative resilience in low-level recognition but suffer a \textbf{functional collapse} in high-order reasoning tasks under stress; \textbf{(II) Scenario Sensitivity:} ``Vocal-like'' interference (e.g., background laughter) proves significantly more destructive than mechanical noise, challenging the model's auditory attention mechanisms; and \textbf{(III) The Denoising Paradox:} Standard speech enhancement often exacerbates performance degradation, as ALLMs prove highly sensitive to the semantic distortions introduced by denoising artifacts.

Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on speech inputs is markedly weaker than on text. This gap could be associated with representational drift across Transformer layers and behavior deviations in long-chain reasoning. To address this issue, we introduce TARS, a reinforcement-learning framework that aligns text-conditioned and speech-conditioned trajectories through an asymmetric reward design. The framework employs two dense and complementary signals: representation alignment, which measures layer-wise hidden-state similarity between speech- and text-conditioned trajectories, and behavior alignment, which evaluates semantic consistency between generated outputs and reference text completions. Experiments on challenging reasoning benchmarks, including MMSU and OBQA, show that our approach significantly narrows the modality reasoning gap and achieves state-of-the-art performance among 7B-scale Speech LLMs.

Text-to-audio (TTA) generation with fine-grained control signals, e.g., precise timing control or intelligible speech content, has been explored in recent works. However, constrained by data scarcity, their generation performance at scale is still compromised. In this study, we recast controllable TTA generation as a multi-task learning problem and introduce a progressive diffusion modeling approach, ControlAudio. Our method adeptly fits distributions conditioned on more fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy. First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme. Second, at the model training stage, we pretrain a diffusion transformer (DiT) on large-scale text-audio pairs, achieving scalable TTA generation, and then incrementally integrate the timing and phoneme features with unified semantic representations, expanding controllability. Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-to-fine sampling nature of DiT. Extensive experiments show that ControlAudio achieves state-of-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations. Demo samples are available at: https://control-audio.github.io/Control-Audio.

Machine Speech Chain, simulating the human perception-production loop, proves effective in jointly improving ASR and TTS. We propose TokenChain, a fully discrete speech chain coupling semantic-token ASR with a two-stage TTS: an autoregressive text-to-semantic model co-trained with ASR and a masked-generative semantic-to-acoustic model for synthesis only. End-to-end feedback across the text interface is enabled with straight-through argmax/Gumbel-Softmax and balanced with supervised ASR via dynamic weight averaging. Ablations examine optimal temperature schedules for in- and cross-domain transfer. Evaluation reveals TokenChain surpasses baseline accuracy 2-6 epochs earlier and yields 5-13% lower equal-epoch error with stable T2S on LibriSpeech, and reduces relative ASR WER by 56% and T2S WER by 31% on TED-LIUM with minimal forgetting, showing that chain learning remains effective with token interfaces and models.

Speech large language models (SLLMs) built on speech encoders, adapters, and LLMs demonstrate remarkable multitask understanding performance in high-resource languages such as English and Chinese. However, their effectiveness substantially degrades in low-resource languages such as Thai. This limitation arises from three factors: (1) existing commonly used speech encoders, like the Whisper family, underperform in low-resource languages and lack support for broader spoken language understanding tasks; (2) the ASR-based alignment paradigm requires training the entire SLLM, leading to high computational cost; (3) paired speech-text data in low-resource languages is scarce. To overcome these challenges in the low-resource language Thai, we introduce XLSR-Thai, the first self-supervised learning (SSL) speech encoder for Thai. It is obtained by continuously training the standard SSL XLSR model on 36,000 hours of Thai speech data. Furthermore, we propose U-Align, a speech-text alignment method that is more resource-efficient and multitask-effective than typical ASR-based alignment. Finally, we present Thai-SUP, a pipeline for generating Thai spoken language understanding data from high-resource languages, yielding the first Thai spoken language understanding dataset of over 1,000 hours. Multiple experiments demonstrate the effectiveness of our methods in building a Thai multitask-understanding SLLM. We open-source XLSR-Thai and Thai-SUP to facilitate future research.

Sound event localization and detection (SELD) involves predicting active sound event classes over time while estimating their positions. The localization subtask in SELD is usually treated as a direction of arrival estimation problem, ignoring source distance. Only recently, SELD was extended to 3D by incorporating distance estimation, enabling the prediction of sound event positions in 3D space (3D SELD). However, existing methods lack input features specifically designed for distance estimation. We address this gap by introducing two novel reverberation-based feature formats: one using the direct-to-reverberant ratio (DRR) and another leveraging signal autocorrelation to capture early reflections. We extensively evaluate and benchmark these features on the STARSS23 dataset, combining them with established SELD features for sound event detection (SED) and direction-of-arrival estimation (DOAE), and testing across different network architectures. Our proposed features, applicable to both FOA and MIC formats, achieve state-of-the-art distance estimation, enhancing overall 3D SELD performance.

In this paper, we propose a novel approach for generating music based on an artificial intelligence (AI) system. We analyze the features of music and use them to fit and predict the music. The fractional Fourier transform (FrFT) and the long short-term memory (LSTM) network are the foundations of our method. The FrFT method is used to extract the spectral features of a music piece, where the music signal is expressed on the time and frequency domains. The LSTM network is used to generate new music based on the extracted features, where we predict the music according to the hidden layer features and real-time inputs using GiantMIDI-Piano dataset. The results of our experiments show that our proposed system is capable of generating high-quality music that is comparable to human-generated music.

Recent Speech-to-Speech Translation (S2ST) systems achieve strong semantic accuracy yet consistently strip away non-verbal vocalizations (NVs), such as laughter and crying that convey pragmatic intent, which severely limits real-world utility. We address this via three contributions. First, we propose a synthesis pipeline for building scalable expressive datasets to overcome the data scarcity limitation. Second, we propose MoVE, a Mixture-of-LoRA-Experts architecture with expressive-specialized adapters and a soft-weighting router that blends experts for capturing hybrid expressive states. Third, we show pretrained AudioLLMs enable striking data efficiency: 30 minutes of curated data is enough for strong performance. On English-Chinese S2ST, while comparing with strong baselines, MoVE reproduces target NVs in 76% of cases and achieves the highest human-rated naturalness and emotional fidelity among all compared systems, where existing S2ST systems preserve at most 14% of NVs.

While recent Spoken Language Models (SLMs) have been actively deployed in real-world scenarios, they lack the capability to discern Third-Party Interruptions (TPI) from the primary user's ongoing flow, leaving them vulnerable to contextual failures. To bridge this gap, we introduce TPI-Train, a dataset of 88K instances designed with speaker-aware hard negatives to enforce acoustic cue prioritization for interruption handling, and TPI-Bench, a comprehensive evaluation framework designed to rigorously measure the interruption-handling strategy and precise speaker discrimination in deceptive contexts. Experiments demonstrate that our dataset design mitigates semantic shortcut learning-a critical pitfall where models exploit semantic context while neglecting acoustic signals essential for discerning speaker changes. We believe our work establishes a foundational resource for overcoming text-dominated unimodal reliance in SLMs, paving the way for more robust multi-party spoken interaction. The code for the framework is publicly available at https://tpi-va.github.io

Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases remain underexplored. Existing speech fairness benchmarks rely on synthetic speech and Multiple-Choice Questions (MCQs), both offering a fragmented view of fairness. We propose VIBE, a framework that evaluates generative bias through open-ended tasks such as personalized recommendations, using real-world human recordings. Unlike MCQs, our method allows stereotypical associations to manifest organically without predefined options, making it easily extensible to new tasks. Evaluating 11 state-of-the-art LALMs reveals systematic biases in realistic scenarios. We find that gender cues often trigger larger distributional shifts than accent cues, indicating that current LALMs reproduce social stereotypes.

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 200 bit per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 3.68% WER on the LibriSpeech test-clean set at 200 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.20% on test-clean and 8.93% on test-other, corresponding to a 13% relative reduction while preserving perceptual quality.

Voice imitation aims to transform source speech to match a reference speaker's timbre and speaking style while preserving linguistic content. A straightforward approach is to train on triplets of (source, reference, target), where source and target share the same content but target matches the reference's voice characteristics, yet such data is extremely scarce. Existing approaches either employ carefully designed disentanglement architectures to bypass this data scarcity or leverage external systems to synthesize pseudo-parallel training data. However, the former requires intricate model design, and the latter faces a quality ceiling when synthetic speech is used as training targets. To address these limitations, we propose MimicLM, which takes a novel approach by using synthetic speech as training sources while retaining real recordings as targets. This design enables the model to learn directly from real speech distributions, breaking the synthetic quality ceiling. Building on this data construction approach, we incorporate interleaved text-audio modeling to guide the generation of content-accurate speech and apply post-training with preference alignment to mitigate the inherent distributional mismatch when training on synthetic data. Experiments demonstrate that MimicLM achieves superior voice imitation quality with a simple yet effective architecture, significantly outperforming existing methods in naturalness while maintaining competitive similarity scores across speaker identity, accent, and emotion dimensions.

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is further hampered by severe data scarcity and the subjective nature of clinical annotations. While semi-supervised learning (SSL) offers a viable path to leverage unlabeled data, existing audio methods often fail to address the core challenge that pathological traits are not uniformly expressed in a patient's speech. We propose a novel, audio-only SSL framework that explicitly models this hierarchy by jointly learning from frame-level, segment-level, and session-level representations within unsegmented clinical dialogues. Our end-to-end approach dynamically aggregates these multi-granularity features and generates high-quality pseudo-labels to efficiently utilize unlabeled data. Extensive experiments show the framework is model-agnostic, robust across languages and conditions, and highly data-efficient-achieving, for instance, 90% of fully-supervised performance using only 11 labeled samples. This work provides a principled approach to learning from weak, far-end supervision in medical speech analysis. The code is available at https://github.com/fispresent/semi_pathological.

Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model's implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently controls text and reference guidance, reducing reliance on reference style while preserving text fidelity. On top of this, we apply style-specific LoRAs together with Orthogonal LoRA Fusion to enable continuous and disentangled multi-attribute control, and introduce a Timbre Consistency Optimization module to mitigate timbre drift caused by weakened reference guidance. Experiments show that ReStyle-TTS enables user-friendly, continuous, and relative control over pitch, energy, and multiple emotions while maintaining intelligibility and speaker timbre, and performs robustly in challenging mismatched reference-target style scenarios.

In this study, we evaluate the efficacy of the Mamba architecture bioacoustics by introducing BioMamba, a Mamba-based audio representation model for wildlife sounds. We pre-train a BioMamba using self-supervised learning on a large audio corpus and evaluate it on the BEANS benchmark across diverse classification and detection tasks. Compared to the state-of-the-art Transformer-based model (AVES), BioMamba achieves comparable performance while significantly reducing VRAM consumption. Our results demonstrate Mamba's potential as a computationally efficient alternative for real-world environmental monitoring.

We present a neuromuscular speech interface that translates electromyographic (EMG) signals recorded from orofacial muscles during speech articulation directly into audio. We find that self-supervised speech (S3) representations are strongly linearly related to the electrical power of muscle activity: a simple linear mapping predicts EMG power from S3 representations with a correlation of r = 0.85. In addition, EMG power vectors associated with distinct articulatory gestures form structured, separable clusters. Together, these observations suggest that S3 models implicitly encode articulatory mechanisms, as reflected in EMG activity. Leveraging this structure, we map EMG signals into the S3 representation space and synthesize speech, enabling end-to-end EMG-to-speech generation without explicit articulatory modeling or vocoder training. We demonstrate this system with a participant with amyotrophic lateral sclerosis (ALS), converting orofacial EMG recorded while she silently articulated speech into audio.

Interactive synthesis of physical sound effects is crucial in digital media production. Sound radiation simulation, a key component of physically based sound synthesis, has posed challenges in the context of complex object boundaries. Previous methods, such as ghost cell-based finite-difference time-domain (FDTD) wave solver, have struggled to address these challenges, leading to large errors and failures in complex boundaries because of the limitation of ghost cells. We present SonicRadiation, a hybrid numerical solution capable of handling complex and dynamic object boundaries in sound radiation simulation without relying on ghost cells. We derive a consistent formulation to connect the physical quantities on grid cells in FDTD with the boundary elements in the time-domain boundary element method (TDBEM). Hereby, we propose a boundary grid synchronization strategy to seamlessly integrate TDBEM with FDTD while maintaining high numerical accuracy. Our method holds both advantages from the accuracy of TDBEM for the near-field and the efficiency of FDTD for the far-field. Experimental results demonstrate the superiority of our method in sound radiation simulation over previous approaches in terms of accuracy and efficiency, particularly in complex scenes, further validating its effectiveness.

To ensure the reliable operation of speech systems across diverse environments, noise addition methods have emerged as the standard solution.However, existing methods offer limited coverage of real-world scenes and depend on pre-existing noise libraries and scene metadata.This paper presents prompt-based Dynamic Generative Scene-based Noise Addition (DGSNA), a novel approach driven by generative language models that integrates Dynamic Generation of Scene-based Information (DGSI) with Scene-based Noise Addition for Speech (SNAS).The DGSI module, with a BET (Background, Examples, Task) prompt framework, dynamically generates logic-compliant scene-based information, including scene dimensions, sound sources, and microphone positions, thereby addressing the challenges of scene enumeration and detailed description.Complementing this, the SNAS module employs a Time-Frequency Diffusion-based (TFD) Text-to-Audio model to synthesize scene-specific noise. By integrating this noise with clean speech via Room Impulse Response (RIR) filters, the module streamlines the traditionally labor-intensive process of replicating diverse acoustic environments.Experimental results show that DGSNA significantly enhances the robustness of speech recognition and keyword spotting models, achieving relative improvements of up to 11.32\%. Furthermore, DGSNA is highly compatible with existing noise addition techniques. Our implementation and demonstrations are available at https://dgsna.github.io.

Multimodal sentiment analysis aims to identify the emotions expressed by individuals through visual, language, and acoustic cues. However, most existing research assume that all modalities are available during both training and testing, which makes their algorithms susceptible to the missing-modality scenarios. In this paper, we propose a novel knowledge-transfer network to translate between different modalities to reconstruct the missing audio features. Moreover, we develop a cross-modality attention mechanism to maximize the information extracted from the reconstructed and observed modalities for sentiment prediction. Extensive experiments on three publicly available datasets demonstrate significant improvements over baseline methods and achieve comparable results to the previous methods with complete multi-modality supervision.

Existing music-driven dance generation approaches have achieved strong realism and effective audio-motion alignment. However, they generally lack semantic controllability, making it difficult to guide specific movements through natural language descriptions. This limitation primarily stems from the absence of large-scale datasets that jointly align music, text, and motion for supervised learning of text-conditioned control. To address this challenge, we propose TeMuDance, a framework that enables text-based control for music-conditioned dance generation without requiring any manually annotated music-text-motion triplet dataset. TeMuDance introduces a motion-centred bridging paradigm that leverages motion as a shared semantic anchor to align disjoint music-dance and text-motion datasets within a unified embedding space, enabling cross-modal retrieval of missing modalities for end-to-end training. A lightweight text control branch is then trained on top of a frozen music-to-dance diffusion backbone, preserving rhythmic fidelity while enabling fine-grained semantic guidance. To further suppress noise inherent in the retrieved supervision, we design a dual-stream fine-tuning strategy with confidence-based filtering. We also propose a novel task-aligned metric that quantifies whether textual prompts induce the intended kinematic attributes under music conditioning. Extensive experiments demonstrate that TeMuDance achieves competitive dance quality while substantially improving text-conditioned control over existing methods.

We introduce a new framework for room acoustics modelling based on a state-space model of the boundary integral equation representing the sound field in a room. Whereas state-space models of linear time-invariant systems are traditionally constructed by means of a state vector and a 4-tuple of system matrices, the state-space representation introduced in this work consists of a state function representing the pressure distribution at the room boundary, and a 4-tuple of integral operators. We refer to this representation as a boundary integral operator state-space (BIOSS) model and provide a physical interpretation for each of the integral operators. As many mathematical operations on vectors and matrices translate to functions and operators, the BIOSS representation can be manipulated to obtain two transfer function representations, having either a feedback or a parallel feedforward structure. Consequently, various equivalent representations for room acoustics are obtained in the BIOSS framework, in the time or frequency domain, and in continuous or discrete space. We discuss two future directions for how the proposed framework can be fertile for research on room acoustics modelling. Firstly, we identify equivalences between the BIOSS framework and various existing room acoustics models (boundary element models, delay networks, geometric models), which may be used to establish relations between existing models and to develop novel room acoustics models. Secondly, we postulate on how concepts from state-space theory, such as observability, controllability, and state realization, can be used for developing new inference and control methods for room acoustics.

Audio deepfakes pose a significant security threat, yet current state-of-the-art (SOTA) detection systems do not generalize well to realistic in-the-wild deepfakes. We introduce a novel \textbf{I}n-\textbf{C}ontext \textbf{L}earning paradigm with comparison-guidance for \textbf{A}udio \textbf{D}eepfake detection (\textbf{ICLAD}). The framework enables the use of audio language models (ALMs) for training-free generalization to unseen deepfakes and provides textual rationales on the detection outcome. At the core of ICLAD is a pairwise comparative reasoning strategy that guides the ALM to discover and filter hallucinations and deepfake-irrelevant acoustic attributes. The ALM works alongside a specialized deepfake detector, whereby a routing mechanism feeds out-of-distribution samples to the ALM. On in-the-wild datasets, ICLAD improves macro F1 over the specialized detector, with up to $2\times$ relative improvement. Further analysis demonstrates the flexibility of ICLAD and its potential for deployment on recent open-source ALMs.

Prior work shows that fine-tuning aligned models on benign data degrades safety in text and vision modalities, and that proximity to harmful content in representation space predicts which samples cause the most damage. However, existing analyses operate within a single, undifferentiated embedding space -- leaving open whether distinct input properties drive the vulnerability differently. Audio introduces a structurally richer problem: a benign sample can neighbor harmful content not only through what is said but through how it sounds, even when its words are entirely innocuous. We present the first systematic study of benign fine-tuning safety in Audio LLMs, evaluating three state-of-the-art models with a proximity-based filtering framework that selects benign audio by embedding-space distance to harmful content. By decomposing proximity into semantic, acoustic, and mixed axes using external reference encoders alongside each model's own internal encoder, we show that benign fine-tuning elevates Jailbreak Success Rate (JSR) from single digits to as high as 87.12%. Crucially, the dominant vulnerability axis and the relative risk of audio versus text fine-tuning are both architecture-conditioned -- determined by how each model's encoder and projector transform audio into the LLM's input space. We propose two defenses: filtering training data to maximize distance from harmful embeddings, and a textual system prompt at inference, both reducing JSR to near-zero without architectural modification. Our mechanistic analysis on two architectures reveals that fine-tuning selectively suppresses the late-layer refusal circuit while the frozen encoder preserves representations, and that even the suppression pattern is architecture-conditioned, mirroring the behavioral asymmetries across modalities. Safety degradation from benign fine-tuning is a qualitatively distinct risk in Audio LLMs.

Empirical studies of recorded performance have conventionally modelled tempo change as a unidirectional historical process, fitting linear regression lines to tempo data plotted against recording year. This paper argues that such approaches impose a false narrative of uniform stylistic evolution on what is, in fact, a plurality of coexisting interpretive traditions. Applying k-means clustering (k=3) to bar-level BPM data from over one hundred recordings of Beethoven's five piano and cello sonatas (Op. 5 Nos. 1 and 2; Op. 69; Op. 102 Nos. 1 and 2) spanning 1930-2012, this study reveals that every movement supports at least two, and usually three, discrete tempo traditions (slow, mid-range, and fast), whose internal regression slopes are negligible (R-squared <= 0.25 in all but one case), demonstrating that each tradition is independently stable across eight decades. The mid-range cluster dominates in all movements, typically comprising 55-70% of recordings. A slow cluster is absent from fast-character movements (Op. 5 Rondos, Op. 69 Scherzo), reflecting a shared rhetorical consensus about their character. The single case of significant intra-cluster drift (Op. 102 No. 1 Allegro con brio, R-squared=0.246, p=0.013) indicates a moderate mid-range deceleration of approximately 3.2 BPM across the study period. No correlation is found between cluster membership and performers' generational, national, or pedagogical backgrounds, suggesting that tempo tradition reflects individual interpretive choice rather than collective cultural inheritance. The paper proposes an ecological model of stylistic change - coexisting traditions shifting in relative prevalence rather than a single tradition evolving - and argues that this reframing has broad implications for how empirical performance studies interpret corpus-level tempo data.

Recent advances in reasoning models have shown remarkable progress in text-based domains, but transferring those capabilities to multimodal settings, e.g., to allow reasoning over audio-visual data, still remains a challenge, in part because of the limited availability of high-quality reasoning data in targeted multimodal combinations. To address this problem, we introduce AVRT, a novel framework that generates high-quality audio-visual reasoning traces from single-modality teacher models. We generate independent vision- and audio-reasoning traces via models specialized to reason over their respective modalities and merge the resulting traces with an LLM merger model. The resulting multimodal traces are used in a supervised fine-tuning (SFT) cold start to adapt the target model to audio-visual reasoning traces first, before training it in a second reinforcement learning stage on larger-scale data. Evaluated on seven audio-visual and audio benchmarks, our 3B and 7B parameter models achieve state-of-the-art results among models of comparable size including OmniBench and DailyOmni for audio-visual and MMAR for audio-only reasoning, showing that cross-modal training also transfers to single-modality tasks and establishing a new training pipeline for multimodal reasoning models.

Fault intensity diagnosis (FID) plays a pivotal role in intelligent manufacturing while neglecting dependencies among target classes hinders its practical deployment. This paper introduces a novel and general framework with deep hierarchical knowledge loss (DHK) to achieve hierarchical consistent representation and prediction. We develop a novel hierarchical tree loss to enable a holistic mapping of same-attribute classes, leveraging tree-based positive and negative hierarchical knowledge constraints. We further design a focal hierarchical tree loss to enhance its extensibility and devise two adaptive weighting schemes based on tree height. In addition, we propose a group tree triplet loss with hierarchical dynamic margin by incorporating hierarchical group concepts and tree distance to model boundary structural knowledge across classes. The joint two losses significantly improve the recognition of subtle faults. Extensive experiments are performed on four real-world datasets from various industrial domains (three cavitation datasets from SAMSON AG and one publicly available dataset) for FID, all showing superior results and outperforming recent state-of-the-art FID methods.

Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark for evaluating full-duplex state-update reasoning under mid-speech interruptions. EchoChain identifies three recurring failure patterns in post-interruption continuations: contextual inertia, interruption amnesia, and objective displacement. The benchmark generates scenario-driven conversations and injects interruptions at a standardized point relative to assistant speech onset, enabling controlled cross-model comparison. In a paired half-duplex control, total failures drop by 40.2% relative to interrupted runs, indicating that many errors are driven by state-update reasoning under interruption rather than task difficulty alone. Across evaluated real-time voice models, no system exceeds a 50% pass rate, showing substantial room for improvement in mid-generation state revision. EchoChain provides a reproducible benchmark for diagnosing state-update reasoning failures in full-duplex voice interaction.

Optical Music Recognition (OMR) aims to convert printed or handwritten music score images into editable symbolic representations. This paper presents an end-to-end OMR framework that combines residual bottleneck convolutions with bidirectional gated recurrent unit (BiGRU)-based sequence modeling. A convolutional neural network with ResNet-v2-style residual bottleneck blocks and multi-scale dilated convolutions is used to extract features that encode both fine-grained symbol details and global staff-line structures. The extracted feature sequences are then fed into a BiGRU network to model temporal dependencies among musical symbols. The model is trained using the Connectionist Temporal Classification loss, enabling end-to-end prediction without explicit alignment annotations. Experimental results on the Camera-PrIMuS and PrIMuS datasets demonstrate the effectiveness of the proposed framework. On Camera-PrIMuS, the proposed method achieves a sequence error rate (SeER) of $7.52\%$ and a symbol error rate (SyER) of $0.45\%$, with pitch, type, and note accuracies of $99.33\%$, $99.60\%$, and $99.28\%$, respectively. The average training time is 1.74~s per epoch, demonstrating high computational efficiency while maintaining strong recognition performance. On PrIMuS, the method achieves a SeER of $8.11\%$ and a SyER of $0.49\%$, with pitch, type, and note accuracies of $99.27\%$, $99.58\%$, and $99.21\%$, respectively. A fine-grained error analysis further confirms the effectiveness of the proposed model.

Brain-computer interfaces (BCIs) for speech restoration hold transformative potential for the approximately 173,000--232,500 individuals worldwide with ALS-related dysarthria. Despite recent progress, high-performance speech BCIs have been demonstrated in only 22--31 patients globally, largely due to limitations in neural decoding accuracy and practical input interfaces. We present iPhoneme, a brain-to-text communication system that jointly addresses these challenges through integrated modeling and interaction design. The system combines a deep learning phoneme decoder based on a modified Conformer architecture (ConformerXL, 192.9M parameters) with a gaze-assisted phoneme input interface that mitigates the Midas touch problem in eye-tracking systems. The acoustic model incorporates a temporal prenet with multi-scale dilated convolutions and bidirectional GRU for neural jitter correction, temporal subsampling for CTC stability, and Pre-RMSNorm stabilization across 12 encoder blocks, trained with AdamW and cosine scheduling. On the interaction side, iPhoneme introduces a chorded gaze-plus-silent-speech paradigm that replaces dwell-time selection, enabling more efficient input. We evaluate the system on the T15 dataset (45 sessions, 8,071 trials) of 256-channel intracranial EEG from speech motor cortex regions. A 6-gram phoneme language model trained on 3.1M sequences, combined with WFST beam search (beam=128), achieves 92.14% phoneme accuracy (7.86% PER) and 73.39% word accuracy (26.61% WER), approximately 3% above prior state-of-the-art. The system operates on CPU with 180 ms latency, demonstrating real-time, high-accuracy brain-to-text communication for ALS.

Recent Video-to-Audio (V2A) methods have achieved remarkable progress, enabling the synthesis of realistic, high-quality audio. However, they struggle with fine-grained temporal control in multi-event scenarios or when visual cues are insufficient, such as small regions, off-screen sounds, or occluded or partially visible objects. In this paper, we propose FoleyDirector, a framework that, for the first time, enables precise temporal guidance in DiT-based V2A generation while preserving the base model's audio quality and allowing seamless switching between V2A generation and temporally controlled synthesis. FoleyDirector introduces Structured Temporal Scripts (STS), a set of captions corresponding to short temporal segments, to provide richer temporal information. These features are integrated via the Script-Guided Temporal Fusion Module, which employs Temporal Script Attention to fuse STS features coherently. To handle complex multi-event scenarios, we further propose Bi-Frame Sound Synthesis, enabling parallel in-frame and out-of-frame audio generation and improving controllability. To support training and evaluation, we construct the DirectorSound dataset and introduce VGGSoundDirector and DirectorBench. Experiments demonstrate that FoleyDirector substantially enhances temporal controllability while maintaining high audio fidelity, empowering users to act as Foley directors and advancing V2A toward more expressive and controllable generation.

We present StereoFoley, a video-to-audio generation framework that produces semantically aligned, temporally synchronized, and spatially accurate stereo sound at 48 kHz. While recent generative video-to-audio models achieve strong semantic and temporal fidelity, they largely remain limited to mono or fail to deliver object-aware stereo imaging, constrained by the lack of professionally mixed, spatially accurate video-to-audio datasets. First, we develop a base model that generates stereo audio from video, achieving performance on par with state-of-the-art V2A models in both semantic accuracy and synchronization. Next, to overcome dataset limitations, we introduce a synthetic data generation pipeline that combines video analysis, object tracking, and audio synthesis with dynamic panning and distance-based loudness controls, enabling spatially accurate object-aware sound. Finally, we fine-tune the base model on this synthetic dataset, yielding clear object-audio correspondence. Since no established metrics exist, we introduce a stereo object-awareness metric and report it alongside a human listening study; the two evaluations exhibit consistent trends. This work establishes the first end-to-end framework for stereo object-aware video-to-audio generation, addressing a critical gap in the field.

Music-driven dance generation is a challenging task as it requires strict adherence to genre-specific choreography while ensuring physically realistic and precisely synchronized dance sequences with the music's beats and rhythm. Although significant progress has been made in music-conditioned dance generation, most existing methods struggle to convey specific stylistic attributes in generated dance. To bridge this gap, we propose a diffusion-based framework for genre-specific 3D full-body dance generation, conditioned on both music and descriptive text. To effectively incorporate genre information, we develop a text-based control mechanism that maps input prompts, either explicit genre labels or free-form descriptive text, into genre-specific control signals, enabling precise and controllable text-guided generation of genre-consistent dance motions. Furthermore, to enhance the alignment between music and textual conditions, we leverage the features of a music foundation model, facilitating coherent and semantically aligned dance synthesis. Last, to balance the objectives of extracting text-genre information and maintaining high-quality generation results, we propose a novel multi-task optimization strategy. This effectively balances competing factors such as physical realism, spatial accuracy, and text classification, significantly improving the overall quality of the generated sequences. Extensive experimental results obtained on the FineDance and AIST++ datasets demonstrate the superiority of GCDance over the existing state-of-the-art approaches.