Semantic speech tokenizers have become a widely used interface for Audio-LLMs, owing to their compact single-codebook design and strong linguistic alignment. However, their focus on linguistic abstraction induces acoustic blindness, limiting their applicability beyond speech-centric tasks. We propose UniAudio-Token, a framework that empowers semantic tokenizers with general audio perception without compromising speech ability. Instead of altering the semantic paradigm, UniAudio-Token mitigates its information loss through two key innovations: (1) Semantic-Acoustic Primitives (SAP) provide structured supervision by decomposing audio into linguistic content, vocal attributes, and auditory-scene primitives; and (2) Semantic-Acoustic Equilibrium (SAE) introduces a content-aware gating mechanism that adaptively restores fine-grained acoustic details from shallow layers. Extensive evaluations show that UniAudio-Token learns comprehensive universal representations while preserving high-fidelity speech generation. When integrated with downstream LLMs, it outperforms all single-codebook baseline tokenizers on both understanding and generation tasks, effectively serving as a unified audio interface. We publicly release all our code, including training and inference scripts, together with the model checkpoints at https://github.com/Tencent/Universal_Audio_Tokenizer.

Conversational automatic speech recognition in Hungarian is constrained by the limited amount of publicly available dialogue-style training data. The BEA-Dialogue corpus addresses this need, but its strictly speaker-disjoint train/dev/eval split reduces the usable material to only 85 hours. In this paper, we introduce BEA-Dialogue+, an expanded version of the corpus that relaxes the split criterion for experimenters and dialogue partners while preserving complete separation of the primary speakers. This results in 200 hours of transcribed natural conversations and enables a controlled study of the trade-off between additional training data and speaker overlap across the splits. We evaluate several Whisper- and FastConformer-based models on both corpus versions, including Serialized Output Training (SOT)-based fine-tuning for dialogue transcription. Our results show that the larger corpus is more challenging for models without fine-tuning, whereas SOT-based adaptation yields consistent improvements in WER, CER, cpWER, and cpCER. Overall, BEA-Dialogue+ provides a substantially larger yet still demanding benchmark for Hungarian dialogue ASR, and a practical resource for training and evaluating dialogue transcription systems.

Simultaneous speech-to-text translation (SimulST) generates translations while speech is still unfolding, requiring a streaming policy that decides when to read and when to write. State-of-the-art approaches rely on attention-based encoder-decoder models where cross-attention provides explicit alignment signals. In contrast, Speech Large Language Models (SpeechLLMs) are decoder-only architectures relying solely on self-attention. This raises a central question: whether decoder self-attention contains sufficiently stable alignment signals to guide the streaming policy. Moreover, existing approaches typically rely on training-based adaptations or heuristic wait-$k$ policies and have not been validated in long-form settings. To fill these gaps, we propose Decoder-Only Attention (DOA), a training-free policy that enables long-form simultaneous translation with off-the-shelf SpeechLLMs by deriving a proxy alignment from self-attention. Experiments on Phi4-Multimodal and Qwen3-Omni show that DOA provides an effective alignment signal for supporting streaming decisions, enabling low-latency long-form SimulST with quality close to offline decoding without retraining.

Transformer-based architectures have significantly advanced the generation of complex symbolic sequences, yet a significant gap remains in achieving fine-grained, interpretable control over discrete signal attributes. This paper investigates the mechanistic interpretability of the Multitrack Music Transformer (MMT) and proposes a framework for deterministic attribute modulation without retraining to bridge this gap via inference-time activation steering. Utilizing the Difference-in-Means (DiffMean) methodology, we isolate latent directions for signal attributes, specifically Pitch and Duration, within the residual stream. We validate the Linear Representation Hypothesis in this domain, achieving high correlation between steering magnitude and attribute shift. To address the inherent feature entanglement in multi-attribute steering, we introduce a Dual Steering framework utilizing Gram-Schmidt Orthogonalization. Experimental results demonstrate that this geometric decoupling reduces conceptual interference and signal degradation compared to naive vector addition, enabling independent deterministic control even against strong autoregressive conditioning.

Reconstructing continuous speech from non-invasive neural recordings is a fundamental problem for probing human auditory perception and building safe, scalable speech brain-computer interfaces. Despite recent progress, intelligible reconstruction remains elusive, as non-invasive recordings are inherently noisy, spatially blurred, and only partially preserve information about perceived speech. Existing methods directly map neural activity to entangled speech representations before synthesizing waveforms with neural vocoders, resulting in spectral-similar but unintelligible results. To overcome these limitations, we introduce MindVoice, a neuro-to-speech reconstruction framework that uses pretrained models to compensate for the incomplete semantic and acoustic information in neural recordings. MindVoice disentangles reconstruction into two complementary pathways: one recovers high-level semantic content, while the other estimates fine-grained acoustic attributes. These inferred representations are then fused with powerful speech generation models and in-context voice cloning to synthesize natural and intelligible utterances. Extensive experiments on EEG and MEG demonstrate that MindVoice substantially outperforms existing methods on various metrics. These results show that pretrained priors provide a principled way to bridge the gap between noisy neural recordings and natural speech, highlighting a promising attempt for auditory neuroscience research and non-invasive speech brain-computer interfaces.

Creating sound for storytelling is crucial to establishing the environment in productions such as films, TV series and video games. This process often involves repeating, layering and recording real objects or using sound libraries, which can be time-consuming and repetitive. To address these challenges, procedural audio, also known as digital foley, offers a solution by allowing sound designers to quickly generate samples. Despite its efficiency, questions remain about the believability of synthetic samples compared to real ones. In our study, we compared synthetic samples generated by an online procedural engine and integrated them with both animated and live-action visuals. Our results indicate that procedural audio is highly effective and perceived as believable in drama and sci-fi scenes, particularly for sound models such as lasers, hits, air and rockets, whereas synthetic sounds weren't as believable in cartoon productions when representing everyday actions. Finally, we identified specific models that needed optimisation and highlighted audio features that needed improvement with feedback from audio professionals.

Controllable music editing is to modify high-level attributes while strictly preserving rhythmic and melodic structures. However, this task is challenged by a semantic-structural entanglement: steering methods often degrade structure to achieve editing performance, while structural adaptors suppress semantic responsiveness. We propose AnchorSteer, a framework that disentangles this tension by coupling structural anchoring with self-discovered semantic steering. The proposed approach probes internal representations to extract interpretable, label-free concept vectors via a self-supervised reconstruction objective, isolating attributes without curated data. During editing, these portable, plug-and-play concept vectors are injected into diffusion hidden manifolds while a structural adaptor enforces consistency. Variants for unconditioned and conditioned injections are provided to balance robustness and semantic strength. Experiments on ZoME-Bench and subjective tests show that the proposed framework outperforms both steering-only and anchoring-only baselines, enabling significant semantic transformations with high-fidelity structural preservation.

Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial information from multimodal inputs. To address these challenges, we propose SwanSphere, a unified streaming framework for high-fidelity spatial audio generation from panoramic videos and text prompts. SwanSphere mainly makes the following contributions: 1) We introduce a causal autoregressive diffusion transformer architecture that enables streaming high-quality spatial audio generation. 2) We design a Spatial Video-Audio Contrastive (SVAC) learning strategy to align the video encoder with the acoustic domain, and further employ a multi-objective online direct preference optimization (ODPO) scheme, resulting in strong spatial perception and robust multimodal spatial audio synthesis. 3) To alleviate the current scarcity of spatial audio datasets, we also develop an automated annotation pipeline for generating detailed spatial captions. Experimental results demonstrate that SwanSphere achieves superior performance in both video-to-spatial and text-to-spatial audio generation tasks. Demos can be found at: https://swanaigc.github.io.

Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduces an agent-assisted training conversion flow that maps paper and code into versioned, runnable training pipelines under a unified protocol on matched open-data subsets. Overall, SURE improves comparability and reproducibility for deployment-oriented evaluation.

Non-contact material identification enables adaptive interaction for embodied intelligence yet faces challenges from geometry-induced variations (e.g., orientation, shape, distance) and single-modality ambiguities. In this paper, we present GaMi, a multimodal material identification system integrating mmWave and acoustic sensing to robustly operate under unconstrained geometric conditions. By leveraging the insight of shared geometric consistency between co-located bimodal sensors, GaMi employs an intra-sample cross-modal subtractive disentanglement framework. By semantically aligning modalities and subtracting the shared geometric context, it isolates intrinsic material features. Furthermore, GaMi incorporates inter-sample contrastive learning to correct the residual interference caused by cross-modal misalignment. Additionally, a pairing-based adaptation strategy between two modalities enables few-shot generalization across devices. Extensive evaluations on 20 materials show that GaMi achieves 95.2% accuracy, outperforming single-modality baselines across unseen geometric conditions.

With the rise of AI-generated audio, watermarking has become widely used for detecting misuse and protecting intellectual property. However, adversaries may try to remove these watermarks, making it critical to evaluate how well watermarking schemes withstand removal attacks. Existing attacks are often impractical: they either noticeably degrade perceptual quality or require access to the watermarking scheme. We propose DiffErase, a black-box watermark removal attack that assumes no knowledge of the target watermarking scheme while maintaining perceptual quality. DiffErase perturbs watermarked audio to an intermediate diffusion noise level and regenerates it using a pretrained denoising model, effectively suppressing watermark signals. Theoretical analysis and extensive experiments demonstrate that inaudible audio watermarks are highly vulnerable: across multiple audio domains, DiffErase consistently removes watermarks while preserving perceptual quality. These findings highlight the need for future audio watermarking designs to consider diffusion-based threats. Code and demos are available at https://differase.github.io/DiffErase/.

3D audio and novel-view acoustic synthesis models are usually evaluated with global metrics.However, global metrics often hide where and why binaural prediction fails. We propose a full-reference diagnostic framework that uses time-frequency audio error maps for magnitude, ILD, IPD, temporal alignment, loudness, and high-frequency failures, forming a 3D Audio Error Map (3DAE Map) for visual inspection. We frame these diagnostics into a model-agnostic benchmark, Spatial Audio Error Bench (3DAE Bench), which takes arbitrary ground-truth and predicted binaural pairs and reports the prediction quality of audio novel-view synthesis models. Experiments on ViGAS outputs over Replay-NVAS and SoundSpaces show different dominant failure modes: temporal misalignment on Replay-NVAS and ILD mismatch on SoundSpaces. Overall, the framework provides interpretable failure-mode summaries and intuitive visual maps for audio Novel-view-synthesis model development optimization.

Recent Singing Voice Synthesis (SVS) advances enable highly realistic but potentially malicious AI covers, making singing voice deepfake detection (SVDD) crucial. Self-Supervised Learning (SSL)-based detectors achieve state-of-the-art performance by fine-tuning speech SSL backbones to capture singing-specific spoof artifacts. Existing adversarial attacks often fail against SSL-SVDD, creating a false impression of inherent robustness. We reveal this stems from two challenges. First, at the objective level, attacks optimize cross-entropy on local surrogates, crossing surrogate-specific boundaries rather than suppressing shared spoof evidence. Second, at the method level, attacks follow the surrogate's dominant gradient direction. In SSL-SVDD, this aligns with fine-tuned artifact-sensitive directions, limiting transferability to unseen detectors - a geometric failure we term the Linearity Trap. To properly evaluate robustness, we propose MARS (Meta-Adversarial Regression of Semantics), a transfer-based black-box framework tailored to SSL-SVDD. Structurally, MARS shifts to hypothesis-evidence manipulation by constructing a natural semantic anchor from the pre-trained SSL space and an artifact anchor from the fine-tuned space. Algorithmically, MARS escapes the Linearity Trap via bi-level optimization: the inner stage induces tangential exploration, while the outer stage guides the audio toward the natural semantic manifold. Experiments on the CtrSVDD benchmark show MARS improves Attack Success Rate (ASR) in in-distribution transfer (13%), out-of-distribution transfer (10%), and cross-task evaluation (36%), highlighting the urgent need for robust SVDD systems.

Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design introduces an integrity dependency on the music knowledge database. We show that an attacker can poison the database by injecting a small number of crafted music captions, causing the system to retrieve malicious captions that bias prompt augmentation and steer generation away from the user's intended function, without modifying the user prompt, retriever, or generator. To achieve the music caption poisoning attack, we propose a dual-layer caption poisoning strategy that preserves high-level retrieval anchors while injecting low-level acoustic descriptors to steer prompt augmentation and downstream music generation toward an attacker-chosen target intent. In a MusicCaps knowledge database, CLAP retriever, and MusicGen pipeline, poisoned generations move substantially closer to the attacker's target, while remaining comparably aligned with the original user query. These results expose a practical integrity risk for retrieval-augmented creative AI systems. Our demo can be found at: https://yizhu-wen.github.io/Mental-Damage/

Speech and audio systems operate in inherently non-stationary environments, yet continual learning (CL) research in this domain, especially in the foundation model era, remains fragmented that fail to account for the coupled, geometry-sensitive nature of acoustic representations. Modern speech foundation models operate over highly entangled, continuous representations that jointly encode linguistic, speaker, and paralinguistic factors within a shared latent space. CL is therefore fundamentally about preserving and evolving shared representation structure rather than retaining isolated task knowledge. In this work, we revisit CL for speech from a representation-centered perspective, and introduce a new taxonomy that organizes CL according to how underlying representation geometry evolves under non-stationary acoustic conditions. We further identify key mismatches between current CL assumptions and speech foundation model behavior, and finally outline a set of open challenges and future research directions.

We study timestamped speaker-attributed automatic speech recognition (SA-ASR) for long-form, multi-party speech with overlap. In this setting, chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Prior Speech-LLM systems tend to prioritize either local diarization or global labeling, lacking the ability to jointly model fine-grained temporal boundaries and robust cross-chunk identity linking. We propose G-STAR, an end-to-end framework that couples a cache-conditioned speaker-tracking module with a Speech-LLM transcription backbone. The tracker provides structured speaker cues with temporal grounding, and the LLM generates attributed text conditioned on these cues. G-STAR supports component-wise optimization and joint end-to-end training, enabling flexible learning under heterogeneous supervision and domain shift. Under chunk-wise decoding protocols, experiments on both oracle-segmented local evaluation and full-meeting global evaluation show strong speaker-attributed transcription performance.

Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS models. Conventional machine unlearning is insufficient in this context, as zero-shot TTS can dynamically reconstruct voices from just reference prompts. We formalize this task as Speech Generation Speaker Poisoning (SGSP), in which we modify trained models to prevent the generation of specific identities while preserving utility for other speakers. We evaluate inference-time filtering and parameter-modification baselines across 1, 15, and 100 forgotten speakers. Performance is assessed through the trade-off between utility (WER) and privacy, quantified using AUC and Forget Speaker Similarity (FSSIM). We achieve strong privacy for up to 15 speakers but reveal scalability limits at 100 speakers due to increased identity overlap. Our study thus introduces a novel problem and evaluation framework toward further advances in generative voice privacy.

Probing is widely adopted in computer vision to faithfully evaluate self-supervised learning (SSL) embeddings, as finetuning may misrepresent their inherent quality. In contrast, audio SSL models still rely on finetuning because simple probing fails to unlock their full potential and alters their rankings when competing on AudioSet. Hence, a robust and efficient probing mechanism is required to guide the trajectory of audio SSL towards reliable and reproducible methods. We introduce Convex Gated Probing (CGP), a prototype-based method that significantly closes the gap between finetuning and probing in audio. CGP efficiently utilizes all frozen layers via a gating mechanism and exposes the location of latent task-relevant information. Guided by CGP as a reliable post-hoc evaluation probe, we rework the entire SSL pipeline of current best performing audio models that use legacy implementations of prior SSL methods. By refining data preprocessing, model architecture, and pretraining recipe, we introduce Better Audio Transformer (BAT), and establish new SOTA on audio benchmarks.

In speech machine learning, neural network models are typically designed by choosing an architecture with fixed layer sizes and structure. These models are then trained to maximize performance on metrics aligned with the task's objective. While the overall architecture is usually guided by prior knowledge of the task, the sizes of individual layers are often chosen heuristically. However, this approach does not guarantee an optimal trade-off between performance and computational complexity; consequently, post hoc methods such as weight quantization or model pruning are typically employed to reduce computational cost. This occurs because stochastic gradient descent (SGD) methods can only optimize differentiable functions, while factors influencing computational complexity, such as layer sizes and floating-point operations per second (FLOP/s), are non-differentiable and require modifying the model structure during training. We propose a reparameterization technique based on feature noise injection that enables joint optimization of performance and computational complexity during training using SGD-based methods. Unlike traditional pruning methods, our approach allows the model size to be dynamically optimized for a target performance-complexity trade-off, without relying on heuristic criteria to select which weights or structures to remove. We demonstrate the effectiveness of our method through three case studies, including a synthetic example and two practical real-world applications: voice activity detection and audio anti-spoofing. The code related to our work is publicly available to encourage further research.

Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursuing state-of-the-art on AudioSet. A key reason is that global pooling creates an information bottleneck causing linear probes to misrepresent the embedding quality: The $\texttt{cls}$-token discards crucial token information about dispersed, localized events in audio. This weakness is rooted in the mismatch between the pretraining objective (globally) and the downstream task (localized). Across a comprehensive benchmark of 13 datasets and 6 spectrogram-based encoders, we investigate the global pooling bottleneck. We introduce binarized prototypical probes: a lightweight and simple pooling method that learns prototypes to perform class-wise information aggregation. Despite its simplicity, our method notably outperforms linear and attentive probing. Our work establishes probing as a competitive and efficient paradigm for evaluating audio SSL models, challenging the reliance on costly fine-tuning.

Electrophysiological (ExG) signals offer valuable insights into human physiology, yet building foundation models that generalize across everyday tasks remains challenging due to two key limitations: (i)~insufficient data diversity, as most ExG recordings are collected in controlled labs with bulky, expensive devices; and (ii)~task-specific model designs that require tailored processing (i.e., targeted frequency filters) and architectures, which limit generalization across tasks. To address these challenges, we introduce an approach for scalable, task-agnostic ExG monitoring in the wild. We collected 50 hours of unobtrusive free-living ExG data with an earphone-based hardware prototype to narrow the data diversity gap. At the core of our approach is Physiology-informed Multi-band Tokenization (PiMT), which decomposes ExG signals into 12 physiology-informed tokens, followed by a reconstruction task to learn robust representations. This enables adaptive feature recognition across the full frequency spectrum while capturing task-relevant information. Experiments on our new DailySense dataset, the first to enable ExG-based analysis across five human senses, together with four public ExG benchmarks, demonstrate that PiMT consistently outperforms state-of-the-art methods across diverse tasks.

Replay speech attacks pose a significant threat to voice-controlled systems, especially in smart environments where voice assistants are widely deployed. While multi-channel audio offers spatial cues that can enhance replay detection robustness, existing datasets and methods predominantly rely on single-channel recordings. Moreover, previous studies highlighted that generalization of this attack to new environments is challenging, requiring new methods for generating data encompassing various acoustic conditions. Hence, in this work we introduce an acoustic simulation framework designed to simulate multi-channel replay speech configurations using publicly available resources. Using the framework, we train the state-of-the-art multi-channel replay detector M-ALRAD and evaluate its generalisation on the ReMASC real-recording corpus without any real training data. To improve the exploitation of spatial information, we extend M-ALRAD with inter-channel phase difference features computed for adjacent microphone pairs, augmenting the beamformed representation with directional cues. Synthetic datasets will be available upon acceptance of the paper.