Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids through waveform patchify and introduce amplitude lifting to align signal scales, enabling stable optimization via direct x-prediction in flow matching. To capture complex semantic alignment and temporal synchronization, we leverage an automated data pipeline to curate 5 million high-quality video-text-audio triplets, allowing the model to learn fine-grained acoustic patterns from scratch. Experimental results show that WavFlow achieves competitive performance on the video-to-audio benchmark VGGSound (FD_PaSST: 59.98, IS_PANNs: 17.40, DeSync: 0.44) and the text-to-audio benchmark AudioCaps (FD_PANNs: 10.63, IS_PANNs: 12.62), matching or exceeding the performance of established latent-based methods. Our work demonstrates that intermediate compression is not a prerequisite for high-quality synthesis, offering a simpler and more scalable alternative for multimodal audio generation.

Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio-codec autoencoder. In this work we introduce SAME (Semantically-Aligned Music autoEncoder), an autoencoder for stereo music and general audio that reaches a 4096$\times$ temporal compression ratio while maintaining reconstruction quality and downstream generative performance. We achieve this by combining a tranformer-based backbone with set of semantic regularisation approaches, phase-aware reconstruction losses and improved discriminator designs. The architecture delivers substantial computational cost benefits, through both its high compression ratio and its reliance on well-optimised transformer primitives. Two variants (a large SAME-L and a CPU-deployable SAME-S) are released in open-weights form.

ADD in real-world scenarios has evolved from speech-only spoofing to more challenging component-level settings, where speech and environmental sounds may be independently manipulated. To tackle this, we propose EnvTriCascade, an Environment-Aware Tri-Stage Cascaded framework for the ESDD2 Challenge. First, a mix-consistency detector provides a binary prior to distinguish original recordings from manipulated mixtures, which calibrates the final decisions. Next, two complementary five-class detectors, leveraging SSLAM+XLS-R and EAT-large+XLS-R representations, extract robust multi-branch features integrated via a cross-branch attention-gated classifier. To enhance robustness against diverse mixing conditions, we incorporate RawBoost augmentation. Trained exclusively on the official CompSpoofV2 dataset, our system achieves a Macro-F1 score of 0.8266 on the test set, significantly outperforming the official baseline and ranking second in the challenge.

Real-time magnetic resonance imaging (rtMRI) of speech production enables non-invasive visualization of dynamic vocal-tract motion and is valuable for speech science and clinical assessment. However, rtMRI is fundamentally constrained by trade-offs among spatial resolution, temporal resolution, and acquisition speed, often leading to undersampled k-space measurements and degraded reconstructions. We propose SIREM, a speech-informed MRI reconstruction framework that uses synchronized speech as a cross-modal prior. The central idea is that vocal-tract configurations during speech are correlated with the produced acoustics, making part of the image content predictable from audio. SIREM models each frame as a fusion of an audio-driven component and an MRI-driven component through a spatial weighting map. The audio branch predicts articulator-related structure from speech, while the MRI branch reconstructs complementary content from measured k-space data. We further introduce a learnable soft weighting profile over spiral arms, enabling a differentiable study of how k-space arm usage interacts with speech-informed fusion. This yields a unified multimodal formulation that combines audio-driven prediction, MRI reconstruction, and sampling adaptation. We evaluate SIREM on the USC speech rtMRI benchmark against standard baselines, including gridding, wavelet-based compressed sensing, and total variation. SIREM introduces a speech-informed reconstruction paradigm that operates in a substantially higher-throughput regime than iterative methods while preserving anatomically plausible vocal-tract structure. These results establish an initial benchmark for multimodal speech-informed rtMRI reconstruction and highlight the potential of synchronized speech as an auxiliary prior for fast reconstruction. The source code is available at https://github.com/mdhasanai/SIREM

The sonata form is a musically rich and hierarchically structured form that poses significant challenges for automatic analysis. While music structure analysis has seen strides of progress in recent years, sonata form analysis remains in its early stages. This is largely due to the time-consuming and high barrier of the music background requirement for annotating classical music structures. To advance research in this area, we curated SoSA-Moz, the first large-scale dataset featuring comprehensive hierarchical structure annotations. This work establishes a foundation for systematic sonata form analysis. Leveraging this newly contributed resource, we further propose Sonalyzer-Moz, a baseline model specifically designed for investigating complex sonata structures. This framework integrates feature aggregation with sequential modeling, enabling it to capture both local feature and upper-level structural dependencies. Experiment results show that Sonalyzer-Moz is capable of identifying the components' boundaries of the upper-level structure that are critical to understanding sonata form. Therefore, this method demonstrates, for the first time, the effectiveness of automatic upper-level analysis of sonata form, and provides a robust baseline for future research in the automatic understanding of sonata form while advancing the study of classical music structure analysis.

The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic optimization, acoustic parameter control, or additive perturbation to embed harmful content into the audio signal. In this work, we challenge this necessity and propose a new paradigm in which the role of audio shifts from content injection to safety alignment interference. We reveal that LALM safety alignment can be compromised solely by specific Acoustic Latent Semantics (ALS), the underlying paralinguistic features intrinsic to the priors of audio generative models. Distinct from previous works that leverage explicit acoustic parameters to merely style malicious audio, we demonstrate that interference audio, benign in content but infused with specific ALS, can serve as a universal jailbreak trigger. Leveraging this insight, we propose the Acoustic Interference Attack (AIA), which decouples the attack payload from the audio. Specifically, AIA employs a set of universal, instruction-neutral interference audio, enabling standard malicious text queries to bypass safety alignment without instance-specific optimization. Extensive experiments on 10 LALMs across five datasets demonstrate that AIA achieves the state-of-the-art attack success rate. Furthermore, our interpretability analysis uncovers the inference path drift induced by AIA and identifies the inherent effective patterns within ALS, revealing the fundamental vulnerability of cross-modal alignment in LALMs.

We introduce a voice-agentic framework that learns one critical omni-understanding skill: knowing when to trust itself versus when to consult external audio perception. Our work is motivated by a crucial yet counterintuitive finding: naively fine-tuning an omni-model on both speech recognition and external sound understanding tasks often degrades performance, as the model can be easily misled by noisy hypotheses. To address this, our framework, Speech-Hands, recasts the problem as an explicit self-reflection decision. This learnable reflection primitive proves effective in preventing the model from being derailed by flawed external candidates. We show that this agentic action mechanism generalizes naturally from speech recognition to complex, multiple-choice audio reasoning. Across the OpenASR leaderboard, Speech-Hands consistently outperforms strong baselines by 12.1% WER on seven benchmarks. The model also achieves 77.37% accuracy and high F1 on audio QA decisions, showing robust generalization and reliability across diverse audio question answering datasets. By unifying perception and decision-making, our work offers a practical path toward more reliable and resilient audio intelligence.

Recent neural audio codecs have achieved impressive reconstruction quality, typically relying on quantization methods such as Residual Vector Quantization (RVQ), Vector Quantization (VQ) and Finite Scalar Quantization (FSQ). However, these quantization techniques limit the geometric structure of the latent space, make it harder to capture correlations between features leading to inefficiency in representation learning, codebook utilization and token rate. In this paper we introduce Two-Dimensional Quantization (Q2D2), a quantization scheme in which feature pairs are projected onto structured 2D grids, such as hexagonal, rhombic, or rectangular tiling and quantized to the nearest grid values, yielding an implicit codebook defined by the product of grid levels, with codebook sizes comparable to conventional methods. Despite its simple geometric formulation, Q2D2 improves audio compression efficiency, with low token rates and high codebook utilization while maintaining state of the art reconstruction quality. Specifically, Q2D2 achieves competitive to superior performance in various objective and subjective reconstruction metrics, across extensive experiments in speech, audio and music domains compared to state of the art models. Comprehensive ablation studies further confirm the effectiveness of our design choices.

This paper presents the Multi-Language Audio Anti-Spoofing Dataset (MLAAD), version 10: a dataset of synthetic audio to train and evaluate audio deepfake detection models. It features 175 Text-to-Speech (TTS) models, comprising a total of 1002.9 hours of synthetic voice in 54 different languages. To evaluate this dataset, we train three state-of-the-art deepfake detection models with MLAAD and observe that it demonstrates superior performance to comparable datasets like InTheWild and FakeOrReal when used as a training resource. Moreover, compared to the renowned ASVspoof 2019 dataset, MLAAD proves to be a complementary resource. In tests across eight datasets, MLAAD and ASVspoof 2019 alternately outperformed each other, each excelling on four datasets. By publishing the dataset and making a trained model accessible via an interactive webserver, we aim to democratize anti-spoofing technology, making it accessible beyond the realm of specialists, and contributing to global efforts against audio spoofing and deepfakes.

Detecting AI-generated music is crucial for preserving artistic authenticity and preventing the misuse of generative music technologies. However, existing discriminative detectors typically rely on generated samples during training and often suffer from severe performance degradation when confronted with music produced by unseen generators, which limits their real-world applicability. To address this issue, we formulate a zero-shot setting for AI-generated music detection, where the detector is trained exclusively on real music without access to any generated samples. Under this setting, we propose MusicDET, a generator-agnostic detection framework based on frequency-guided normalizing flows that probabilistically models the distribution of real music features. By evaluating the likelihood of an input sample under the learned real-music distribution, MusicDET enables effective detection of out-of-distribution music signals. Experiments on the FakeMusicCaps and SONICS datasets show that MusicDET consistently outperforms conventional discriminative detectors, particularly when detecting music generated by previously unseen models.

Stable Audio 3 is a family of fast latent diffusion models (small, medium, large) for variable-length audio generation and editing. Since our models can generate several minutes of audio, variable-length generations are key to avoid the cost of producing full-length generations for short sounds. We also support inpainting, enabling targeted audio editing and the continuation of short recordings. Our latent diffusion models operate on top of a novel semantic-acoustic autoencoder that projects audio into a compact latent space, enabling efficient diffusion-based generation while preserving audio fidelity and encouraging semantic structure in the latent. Finally, we run adversarial post-training to both accelerate inference and improve generation quality, reducing the number of inference steps while improving fidelity and prompt adherence. Stable Audio 3 models are trained on licensed and Creative Commons data to generate music and sounds in less than a 2s on an H200 GPU and less than a few seconds on a MacBook Pro M4. We release the weights of small and medium, that can run on consumer-grade hardware, together with their training and inference pipeline.

The rapid advancement of generative AI has made audio deepfakes increasingly indistinguishable from authentic human vocals, posing significant threats to persons-of-interest (POI) such as public figures. Current detection systems primarily rely on generic, black-box models that fail to capture speaker-specific idiosyncratic traits and lack interpretability. In this paper, we propose Phoneme-based Voice Profiling (PVP), a novel personalized defense framework. By shifting the detection paradigm from macro-utterance analysis to micro-phonetic modeling, PVP captures the unique acoustic distributions underlying a POI's habitual articulatory patterns. Specifically, our framework models speaker-specific phonetic realizations using lightweight Gaussian Mixture Models (GMMs) estimated solely from bona fide reference speech. This design enables data-efficient profiling and robust generalization to previously unseen spoofing attacks without requiring heavy spoof-specific training. Furthermore, we introduce the first large-scale Chinese POI deepfake dataset to benchmark speaker-specific detection. Experimental results demonstrate that PVP significantly outperforms state-of-the-art generic detectors in POI spoofing scenarios, achieving substantial EER reductions while providing fine-grained, phoneme-level interpretability for forensic analysis. Code and data are available at: https://github.com/JunXue-tech/PVP

Weakly labeled datasets such as AudioSet have driven recent progress in audio tagging. However, annotation quality varies across sound classes. Labels may be incomplete, ambiguous, or unreliable, which introduces class-dependent supervision bias during optimisation. The issue becomes harder as real and generated audio are increasingly mixed in training, and generated samples do not always match their intended semantic labels. Prior work mainly addressed unreliable supervision from missing-positive labels, while this paper targets three other sources of unreliable supervision: spurious additions, misassignments between similar classes, and weakened label evidence. These effects introduce class-dependent optimisation bias that is not explicitly modeled by most existing methods. To bridge this gap, the paper proposes a Class-wise Supervision Unreliability (CSU) framework that controls supervision strength at the class level during training. CSU learns a separate unreliability parameter for each class and down-weights less reliable supervision without changing the model architecture or inference process. To support evaluations, this paper also introduces ESC-FreeGen50, a manually verified benchmark of 50 sound classes that combines real and generated audio. Experiments on controlled benchmarks and AudioSet show that CSU improves robustness across different architectures and different sources of supervision unreliability. The results indicate that explicit class-wise modeling of supervision unreliability is an effective and practical strategy for robust audio tagging under large-scale weakly labeled training. Code and data are available at: https://github.com/Yuanbo2020/CSU

The landscape of joint audio and video generation has been fundamentally transformed by the advent of powerful foundation models. Despite these strides, achieving cohesive multimodal customization for the simultaneous preservation of visual identities and vocal timbres across multiple interacting subjects remains largely underexplored. To bridge this gap, we present Omni-Customizer, an end-to-end framework targeted at the precise binding and seamless fusion of multimodal identity information. Specifically, we introduce an Omni-Context Fusion (OCF) module that effectively enriches the base textual prompt with dense, multimodal identity cues, along with a Masked TTS Cross-Attention (MTP-CA) mechanism explicitly designed to prevent the severe "speech leakage" problem. Within this architecture, we propose Semantic-Anchored Multimodal RoPE (SA-MRoPE) to anchor visual and audio reference tokens, along with TTS embeddings, to their corresponding semantic descriptions, enabling structured multimodal fusion and robust identity binding. Furthermore, we devise a comprehensive training strategy that incorporates interleaved audio-video scheduling to rapidly adapt the audio branch to multilingual scenarios without degrading foundational priors, and a progressive in-pair to cross-pair curriculum to facilitate the learning of high-level and robust identity features. Extensive experiments demonstrate that Omni-Customizer achieves state-of-the-art performance in dual-modal customized generation, excelling across visual identity similarity, timbre consistency, precise audio-video synchronization, and overall video-audio fidelity.

This paper describes a novel paradigm that formalizes automatic piano transcription (APT) as an optimal transport (OT) problem, not as a frame-level multi-label binary classification problem. Our method learns to minimize the cost of transporting a predicted distribution of note events to the ground-truth distribution over time and frequency. The OT loss can thus accommodate temporal misalignment, leading to perceptually relevant optimization. We also propose a convolutional recurrent neural network (CRNN) with a harmonics-aware attention mechanism to capture the spectro-temporal dependencies inherent in music.Our experiments using the MAESTRO dataset showed that our method attained a state-of-the-art performance in onset detection. We confirmed the versatility of the OT loss in application to existing models.

While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public datasets or complex multi-stage training. In this paper, we propose TED-TTS, a training-free controllable framework for pretrained zero-shot TTS to enable intra-utterance emotion and duration expression. Specifically, we propose a segment-aware emotion conditioning strategy that combines causal masking with monotonic stream alignment filtering to isolate emotion conditioning and schedule mask transitions, enabling smooth intra-utterance emotion shifts while preserving global semantic coherence. Based on this, we further propose a segment-aware duration steering strategy to combine local duration embedding steering with global EOS logit modulation, allowing local duration adjustment while ensuring globally consistent termination. To eliminate the need for segment-level manual prompt engineering, we construct a 30,000-sample multi-emotion and duration-annotated text dataset to enable LLM-based automatic prompt construction. Extensive experiments demonstrate that our training-free method not only achieves state-of-the-art intra-utterance consistency in multi-emotion and duration control, but also maintains baseline-level speech quality of the underlying TTS model. Code and audio samples are available.

Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to produce physically plausible sounds. Previous benchmarks primarily focus on audio-video temporal synchronization, while largely overlooking explicit evaluation of audio-physics grounding, thereby limiting the study of physically plausible audio-visual generation. To address this issue, we present PhyAVBench, the first benchmark that systematically evaluates the audio-physics grounding capabilities of T2AV, image-to-audio-video (I2AV), and video-to-audio (V2A) models. PhyAVBench offers PhyAV-Sound-11K, a new dataset of 25.5 hours of 11,605 audible videos collected from 184 participants to ensure diversity and avoid data leakage. It contains 337 paired-prompt groups with controlled physical variations that drive sound differences, each grounded with an average of 17 videos and spanning 6 audio-physics dimensions and 41 fine-grained test points. Each prompt pair is annotated with the physical factors underlying their acoustic differences. Importantly, PhyAVBench leverages paired text prompts to evaluate this capability. We term this evaluation paradigm the Audio-Physics Sensitivity Test (APST) and introduce a novel metric, the Contrastive Physical Response Score (CPRS), which quantifies the acoustic consistency between generated videos and their real-world counterparts. We conduct a comprehensive evaluation of 17 state-of-the-art models. Our results reveal that even leading commercial models struggle with fundamental audio-physical phenomena, exposing a critical gap beyond audio-visual synchronization and pointing to future research directions. We hope PhyAVBench will serve as a foundation for advancing physically grounded audio-visual generation. Prompts, ground-truth, and generated video samples are available at https://github.com/imxtx/PhyAVBench.

Learning the violin is harder than it looks. Unlike piano keys or guitar frets, the violin neck has no markings at all, so a beginner cannot tell by looking where to place each finger. MusicSynth is an open-source web tool that tries to fix that: user uploads a photo of any violin sheet music (or a digital score file), and the system automatically produces a video showing a violin fingerboard with each note highlighted at the right moment -- no software to install, no manual note entry required. The system connects three existing open-source tools into one pipeline: an optical music recognition (OMR) library reads the notes from the uploaded image, a MusicXML parser extracts timing information from digital scores, and a video renderer draws the fingerboard frame by frame. The only part built from scratch is the lookup table that maps each musical note to a string and finger position on the violin. Tested across 110 public-domain violin scores, MusicSynth correctly identified 91.2\,\% of notes in clean printed music and assigned the right finger position 99.1\,\% of the time when given a digital score file. To the author's knowledge, no freely available tool currently turns a sheet music image into an animated violin fingerboard tutorial automatically and in a single browser-based step.

Latent diffusion models have emerged as the dominant paradigm for many generation tasks including audio generation such as text-to-audio, text-to-music and text-to-speech. A key component of latent diffusion is an autoencoder (VAE) that compresses high-dimensional signals into a low frame rate continuous representation that is conducive for downstream prediction. Regularizing these VAEs is challenging, as there is a trade-off between over-regularized (poor output quality) and under-regularized (difficult to predict) latent representations. We propose a framework for studying this trade-off through compression and train Audio VAEs at specific bitrates via target-KL regularization. This allows direct comparison to well-studied discrete neural audio codec models, and the construction of rate-distortion curves for audio VAEs. We evaluate the impact of target-KL regularization on text-to-sound generation and find that sweeping compression rates is helpful in identifying the optimal generation setting.

Early detection of exacerbations in asthma and chronic obstructive pulmonary disease (COPD) is important for timely intervention. Speech has emerged as a promising tool for continuous, non-invasive respiratory disease monitoring. However, speech signals inherently carry speaker-identifiable attributes that may dominate model predictions, which may compromise both diagnosis performance and patient privacy. Furthermore, the acoustic features associated with respiratory disease and speaker identity remain unclear in respiratory disease monitoring. We propose an adversarial learning architecture that disentangles pathology-related acoustic patterns from speaker-identifiable attributes. The framework optimizes two clinically hierarchical tasks: (i) respiratory status classification (stable vs. exacerbated) and (ii) exacerbation type classification (asthma exacerbation vs. COPD exacerbation). Speaker identity is suppressed through gradient reversal-based adversarial training. To enhance clinical interpretability, we employ SHapley Additive exPlanations (SHAP) to quantify the contributions of acoustic features to pathology-related predictions versus speaker identity. On the TACTICAS dataset, our method outperforms the single-task baseline across both tasks. For the respiratory status task (stable vs. exacerbated), the AUC improves from 0.897 to 0.910. For the exacerbation type task (asthma exacerbation vs. COPD exacerbation), the AUC increases from 0.674 to 0.793. Concurrently, the J-ratio decreases, confirming effective suppression of speaker information. SHAP analysis reveals the contributions of the acoustic features to both tasks. External validation on the Bridge2AI-Voice dataset further demonstrates consistent performance improvement and reduced speaker dependency, confirming cross-dataset generalizability.

Distributed Acoustic Sensing (DAS) has emerged as a transformative technology for near-surface site characterization. When a vertical source is activated along the fiber, DAS measures only the in-line (radial) component of Rayleigh-wave motion. Dispersion data extracted from radial-component waveforms may differ from those obtained from vertical-component measurements, particularly under complex stratigraphic conditions. Hence, a component-consistent forward problem is desired when inverting radial-component DAS dispersion data to retrieve accurate shear wave velocity (Vs) profiles. This study presents a radial-component predominant-mode (RCPM) inversion framework designed for DAS-based surface-wave analysis that explicitly accounts for source-receiver directivity and modal sensitivity of the Rayleigh-wave radial component. The proposed approach matches measured dominant radial dispersion trends with the theoretical mode exhibiting the maximum modal participation. As a result, the RCPM framework eliminates the need for explicit modal indexing, provides a component-consistent interpretation of radial-component dispersion data, and substantially reduces reliance on subjective analyst-driven modal interpretations. The RCPM approach is systematically evaluated using three synthetic ground models and two field DAS datasets. The synthetic results demonstrate that modal energy distribution differs significantly between vertical and radial components in the presence of strong velocity contrasts and velocity reversals, and that conventional inversion approaches may misinterpret modal behavior, resulting in less accurate Vs profiles. In contrast, the RCPM method consistently captures the correct modal response and yields reliable Vs profiles. Application to two field DAS datasets further demonstrates good agreement between the inverted Vs profiles and independent invasive borehole measurements.

Driven by the escalating global burden of mental health conditions, music-based interventions have attracted significant attention as a non-invasive, cost-effective modality for emotion regulation and psychological stress relief. However, current digital music services rely on static preferences and fail to adapt to users' instantaneous psychological states. Furthermore, directly mapping electroencephalography (EEG) to music generation remains challenging due to severe paired-data scarcity and a lack of interpretability. To address these limitations, we propose MindMelody, a fully functional, closed-loop real-time system for EEG-driven personalized music intervention. MindMelody introduces an emotion-mediated semantic bridge. Specifically, a hybrid Transformer-GNN first decodes real-time EEG signals into global Valence-Arousal states and local temporal affect trajectories. These states are then fed into a Retrieval-Augmented Generation (RAG)-equipped Large Language Model (LLM) to formulate structured intervention plans. Subsequently, a novel Hierarchical EEG Controller injects global affect prefixes and local temporal guidance into a pretrained music backbone, enabling fine-grained controllable audio synthesis. Crucially, the system incorporates a continuous feedback loop that updates generation parameters on the fly based on the user's evolving EEG dynamics. Extensive experiments show that MindMelody improves control adherence and emotional alignment, and receives higher perceived helpfulness in a short-term listening setting, suggesting its promise as an adaptive affect-aware music generation framework.

Speech Continuation (SC) is the task of generating a coherent extension of a spoken prompt while preserving both semantic context and speaker identity. Because SC is constrained to a single audio stream, it offers a more direct setting for probing biases in speech foundation models than dialogue does. In this work we present the first systematic evaluation of bias in SC, investigating how gender and phonation type (breathy, creaky, end-creak) affect continuation behaviour. We evaluate three recent models: SpiritLM (base and expressive), VAE-GSLM, and SpeechGPT across speaker similarity, voice quality preservation, and text-based bias metrics. Results show that while both speaker similarity and coherence remain a challenge, textual evaluations reveal significant model and gender interactions: once coherence is sufficiently high (for VAE-GSLM), gender effects emerge on text-metrics such as agency and sentence polarity. In addition, continuations revert toward modal phonation more strongly for female prompts than for male ones, revealing a systematic voice-quality bias. These findings highlight SC as a controlled probe of socially relevant representational biases in speech foundation models, and suggest that it will become an increasingly informative diagnostic as continuation quality improves.

With the fast development of zero-shot text-to-speech technologies, it is possible to generate high-quality speech signals that are indistinguishable from the real ones. Speech editing, including speech insertion and replacement, appeals to researchers due to its potential applications. However, existing studies only considered clean speech scenarios. In real-world applications, the existence of environmental noise could significantly degrade the quality of generation. In this study, we propose a noise-resilient speech editing framework, SeamlessEdit, for noisy speech editing. SeamlessEdit adopts a frequency-band-aware noise suppression module and an in-content refinement strategy. It can well address the scenario where the frequency bands of voice and background noise are not separated. The proposed SeamlessEdit framework outperforms state-of-the-art approaches in multiple quantitative and qualitative evaluations.

Congenital anomalies arising as a result of a defect in the structure of the heart and great vessels are known as congenital heart diseases or CHDs. A PCG can provide essential details about the mechanical conduction system of the heart and point out specific patterns linked to different kinds of CHD. This study aims to investigate the minimum signal duration required for the automatic classification of heart sounds. This study also investigated the optimum signal quality assessment indicator (Root Mean Square of Successive Differences) RMSSD and (Zero Crossings Rate) ZCR value. Mel-frequency cepstral coefficients (MFCCs) based feature is used as an input to build a Transformer-Based residual one-dimensional convolutional neural network, which is then used for classifying the heart sound. The study showed that 0.4 is the ideal threshold for getting suitable signals for the RMSSD and ZCR indicators. Moreover, a minimum signal length of 5s is required for effective heart sound classification. It also shows that a shorter signal (3 s heart sound) does not have enough information to categorize heart sounds accurately, and the longer signal (15 s heart sound) may contain more noise. The best accuracy, 93.69%, is obtained for the 5s signal to distinguish the heart sound.

We present vega-mir, an open-source Python library that bundles nine information-theoretic and statistical metrics for the analysis of symbolic music corpora behind a small, tested, citable API, and demonstrates two of them at corpus scale in case studies not addressed by the upstream Cygnus paper. Of the nine metrics, three (Shannon entropy, Kullback-Leibler divergence, Zipfian fits) were deployed in the companion Cygnus arXiv preprint; two (network analysis on chord-transition graphs and spectral analysis of rubato curves) are deployed in full case studies here; the four remaining (multi-dimensional Gini, chi-squared stationarity, Higuchi fractal dimension, interval distribution) are validated against analytic anchors and exercised as sanity checks on a bundled 8-composer dataset. The two case studies yield two main observations. First, on the fourteen MAESTRO composers with N >= 10 pieces, the PageRank value of the gravity-centre node correlates with the marginal Kullback-Leibler distance at rho = 0.61 (Spearman, composer-level jackknife N = 14); the categorical gravity-centre identity takes five distinct values across the corpus but is not itself correlated with marginal KL (rho = 0.13, p = 0.21). Second, on the 247-piece Bach multi-master corpus (Schiff, Gould, Richter), Gould holds the highest periodicity ratio of the three performers, not the lowest, inverting the cliché that low scalar rubato reads as "metronomic": Gould's rubato is small in amplitude but structured in time, with a median dominant period of 66 beats against Schiff's 102 and Richter's 104.

Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate acoustic information, rather than verifying the audio stream. This issue appears across both state-of-the-art open-source omni models and leading closed-source models from providers such as Google and OpenAI. We characterize this failure mode as an audio-visual Clever Hans effect, in which models appear (falsely) audio-grounded, but actually exploit visual-acoustic correlations without verifying whether the audio and visual streams are truly aligned. To systematically study this behavior, we introduce Thud, an intervention-driven probing framework based on three counterfactual audio edits: Shift, which tests temporal synchronization; Mute, which tests sound existence; and Swap, which tests audio-visual consistency. Beyond diagnosis, we further study a two-stage alignment recipe: intervention-derived preference pairs teach audio verification, while event-level general video preferences regularize the model against over-specialization. Our best 10K-sample recipe improves average performance across the three intervention dimensions by 28 percentage points, while slightly improving performance on general video and audio-visual QA benchmarks.

Large Language Models (LLMs) voice assistants are commonly built as cascaded Automatic Speech recognition (ASR) to LLM systems, where recognition errors can distort user intent. Dislikes may also arise from ambiguous, out-of-domain, or non-request turns, making it hard to isolate ASR effects. We release WASIL (it denotes connection or linking in Arabic): in-the-wild Arabic spoken interaction prompts with audio, ASR hypotheses, assistant responses, and explicit like/dislike feedback (8,529 turns; 14.2% dislikes), plus a 2,000-turn test set covering Modern Standard Arabic (MSA) and four major dialects with their labels. We provide low-cost gold transcripts via multi-ASR agreement-guided post-editing and annotate answerability (answerable, ambiguous/needs-clarification, unsupported, not-a-request/noise) to separate intrinsic unanswerability from ASR-induced degradation. Finally, we describe scalable reference-free evaluation of responses from ASR vs. gold transcripts using multi-judge LLM scoring.

Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by distilling a one-step consistency model from a multi-step diffusion-based teacher model. However, distilled consistency models are inherently biased towards the sampling trajectory of the teacher model, making them less robust to noise and prone to inheriting inaccuracies from the teacher model. To address this limitation, we propose ROSE-CD: Robust One-step Speech Enhancement via Consistency Distillation, a novel approach for distilling a one-step consistency model. Specifically, we introduce a randomized learning trajectory to improve the model's robustness to noise. Furthermore, we jointly optimize the one-step model with two time-domain auxiliary losses, enabling it to recover from teacher-induced errors and surpass the teacher model in overall performance. This is the first pure one-step consistency distillation model for diffusion-based speech enhancement, achieving 54 times faster inference speed and superior performance compared to its 30-step teacher model. Experiments on the VoiceBank-DEMAND dataset demonstrate that the proposed model achieves state-of-the-art performance in terms of speech quality. Moreover, its generalization ability is validated on both an out-of-domain dataset and real-world noisy recordings.

Automatic Speaker Verification (ASV) systems, which identify speakers based on their voice characteristics, have numerous applications, such as user authentication in financial transactions, exclusive access control in smart devices, and forensic fraud detection. However, the advancement of deep learning algorithms has enabled the generation of synthetic audio through Text-to-Speech (TTS) and Voice Conversion (VC) systems, exposing ASV systems to potential vulnerabilities. To counteract this, we propose a novel architecture named AASIST3. By enhancing the existing AASIST framework with Kolmogorov-Arnold networks, additional layers, encoders, and pre-emphasis techniques, AASIST3 achieves a more than twofold improvement in performance. It demonstrates minDCF results of 0.5357 in the closed condition and 0.1414 in the open condition, significantly enhancing the detection of synthetic voices and improving ASV security. \textbf{The new version of the model is publicly available at \href{https://huggingface.co/lab260/Spectra-AASIST3}{\underline{HuggingFace (2026)}}}