ALT In speech enhancement, standard supervised training requires pairs of noisy and clean speech. Such pairs are typically created by artificially degrading clean speech, leading to a domain mismatch between synthetic training data and real recordings. Noisy target training (NyTT) mitigates this limitation by training an enhancement model to predict a noisy recording from a noisier version generated by adding extra noise. However, since the training target is noisy, NyTT might learn to leave residual noise in the enhanced output. In this paper, we address this issue in NyTT by incorporating a Sinkhorn drifting loss that matches the distribution of the enhanced speech to that of unpaired clean speech. The Sinkhorn drifting loss attracts enhanced speech toward high-density regions of the clean-speech distribution while repelling it from the current enhanced-speech distribution in latent space. This loss uses only unpaired clean speech rather than the clean counterpart of each degraded record

ALT Surgical scene understanding is a prerequisite for context-aware and intelligent systems in the operating room. Current methods rely mostly on visual data, while acoustic sensing has shown potential to provide complementary information on surgical activity. First approaches for the localisation of surgical activity relied on microphone arrays and acoustic beamforming. This work investigates whether the active instrument can be localized from a single microphone and a camera by learning the correspondence between the appearance and the sound of surgical instruments, without annotating its position. We adapt weakly supervised audio-visual localisation, which learns from the co-occurrence of image and sound, to the surgical setting. We record simulated surgical actions, sawing, drilling, and chiseling, and train the model on these recordings without any spatial annotation to produce a heatmap over the sounding tool. We extend the training objective by two terms: a silence term, which supp

ALT Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps. First, standard benchmarks fix the number of speakers at two and ignore the near-/far-field interference, reverberation, and sudden noise of real scenes. Second, high-performance causal architectures are too heavy for edge deployment. Lightweight alternatives try to reclaim capacity by repeatedly invoking a small separator, which offsets the savings. To address the first gap, we release RealSSA, a realistic AVTSE benchmark consisting of RealSSA-Sim and RealSSA-Real. RealSSA-Sim provides controllable simulated scenes with 1–5 dynamic near-field interfering speakers; scenes with far-field interference additionally include 10–15 far-field interfering speakers. RealSSA-Real provides a held-out real-recorded evaluation set. To address the second gap, we propose Falcon, a causal AVTSE method. Its Separator performs multi-scale time-f

ALT Singing emotion recognition relies predominantly on deep learning models that achieve strong performance but offer limited insight into the vocal characteristics driving emotion, of- ten overlooking the singing voice as a distinct signal. We propose an interpretable singing emotion recognition framework using a compact set of singing-specific descriptors across prosody, spec- tral features, phonetics, and vocal technique. To decode model decisions and link predictions to measurable acoustic phenomena, we employ SHAP and apply GRAD-CAM to qualitatively assess the learned representations of vocal techniques. Evaluations show that singing-specific features reduce cross-singer variability, while vocal technique descriptors provide interpretable insights into singing expression. Furthermore, out-of-domain evaluation on VocalSet reveals interesting associations between emotional expression and ground-truth technical execution. The analysis highlights vibrato and pharyngeal techniques as sali

ALT People differ in how they perceive music, what associations they make with it, what they like about it, and how they respond to it. Computational models intended to simulate people in environments that include music should account for these differences. Although LLMs have been shown to reproduce aspects of human behavior, whether audio-language models (ALMs) can reproduce a specific person's responses to textual and musical stimuli remains underexplored. We introduce MusicTwins, a framework that combines persona summaries, personal memory, and post-training to generate person-specific responses. We construct persona representations from human writings, capturing background, views, personality, writing style, and a musical profile, and post-train Audio Flamingo Next through supervised fine-tuning and reinforcement learning. Evaluation on ten held-out personas shows notable improvements for Audio Flamingo Next in persona fidelity, including personality, writing style, and responses to mu

ALT Music-driven group dance generation must decide not only how each dancer moves, but also what formation the group should form, when it should change, and who should execute each transition. Existing methods can generate orderly and rhythmically synchronized group motion, but remain limited in formation evolution and inter-dancer interaction. In human choreography, formation transitions often align with changes in high-level musical structure, such as the progression from an introduction to a chorus or from a chorus to a climax. We present ChoreoStudio, which makes choreography planning explicit. A music disentangler first decomposes the audio into frame-level rhythmic features and segment-level structural features. Given the segment-level features and sparse labels, a frozen omni-modal model acts as a scriptwriter, producing a global semantic description that guides the Director's choreography planning. Based on this context, the Director produces three coupled interaction decisions: a

ALT The interior sound of an electric vehicle is a superposition of several distinct noise contributions - wind noise, tire noise, powertrain (electric drive unit and inverter) noise, and auxiliary-drive noise - whose relative balance governs both the overall loudness and the perceived sound quality in the vehicle interior. Decomposing a recorded vehicle interior signal into these source contributions is a prerequisite for targeted acoustic engineering, but requires effortful measurement campaigns as well as expertise in the field of transfer path analysis. This work formulates the decomposition as a supervised, binaural source-separation problem with four target source contributions and adapts a hybrid time-spectrogram transformer architecture, originally developed for music demixing, to the domain of sound source separation for technical systems. To disambiguate source contributions, conditioning is introduced in the form of operating-state information, including electric drive speed, el

ALT Sparse autoencoders (SAEs) can expose features of a generative model without predefined labels, but in language models the evidence used to interpret these features has proven an unreliable guide to which of them steer the output. Whether interpretations of SAE features predict control in music generators has not, to our knowledge, been tested. We develop an end-to-end protocol for discovering and evaluating SAE features in text-to-MIDI generation and apply it to text2midi and MIDI-LLM. The protocol characterizes features through correlations with musical metrics, shared instrument programs, and automated descriptions, each with its own control: note-density adjustment, matched inactive excerpts, and permutation calibration. It then tests candidates by intervention, measured directly in the generated MIDI against unmodified generation and a matched random direction, ranks them in screens, and confirms selected features on new prompts. Evidence that survives these controls points to fea

ALT Text-to-speech (TTS) is usually evaluated by transcribing its output with an automatic speech recognition (ASR) system, so the word error rate also counts recognizer errors. We measure these errors on human recordings of the test sentences. On LibriSpeech and FLEURS, the evaluation recognizer misses 33-67% of very rare words even in human speech, and all three recognizers miss 22-42%. Checking every word with two more recognizer families lowers the apparent TTS error on words that at least one recognizer hears two- to three-fold (very rare LibriSpeech words: from 10-13% to 3-5%), yet very rare words remain the hardest. Ignoring words the recognizer misses in human speech is biased: the other recognizers find TTS errors far more often on these words (4-6% vs. 0.2-0.3%) and overturn about half of the errors this mask keeps. As half of the remaining adjudicated errors may be spelling variants, a listening test is needed.

ALT Underwater acoustic passive detection is essential to maritime surveillance and intelligent ocean sensing. Existing detection systems typically collapse multichannel array observations into a binary decision or a scalar confidence score, offering limited insight into the physical evidence that supports or contradicts a target declaration. This limitation is acute at low signal-to-noise ratio (SNR), where isolated spectral peaks and transient beamforming responses are inherently ambiguous and physically verifiable targets are characterized by an ensemble of coupled reinforcing cues. Building on the unified from-signals-to-evidence framework introduced in the companion Part I, this paper instantiates the framework for passive target detection. A physics-aware multichannel acoustic encoder encodes the array observations into complementary acoustic evidence tokens through a direction-guided architecture that combines minimum variance distortionless response (MVDR) processing with time-freq

ALT Long-form temporal audio grounding (TAG) is challenging because target events often occupy only a small portion of a recording, while queries may impose multiple semantic constraints over a large temporal search space. We propose a query-conditioned liquid temporal grounding framework that injects query semantics through FiLM before a closed-form continuous-time (CfC) network models long-range temporal dependencies. Multiple query-relevant candidates are generated, from which a frozen large audio-language model selects the most compatible one for lightweight local boundary refinement. The pretrained backbone remains frozen, with only lightweight grounding modules optimized. Experiments on the English TAG subset of LAT-Bench show consistent improvements across MOSS-Audio and Qwen3-Omni, while ablations confirm the complementary roles of FiLM and CfC.

ALT Transformer-based models have shown strong performance across diverse tasks, but their reliance on self-attention mechanisms often leads to high computational costs. Token sparsification, which reduces the number of tokens processed in transformer layers, offers a promising solution to maintain performance while improving efficiency. However, although widely studied in the vision and language domains, token sparsification remains underexplored in audio, with existing work often limited to a single method, model size, or dataset. This work presents a comprehensive evaluation of token sparsification techniques for audio transformers. We assess a range of token pruning and merging strategies across multiple datasets and model sizes, under both post-training and fine-tuning settings. Furthermore, we introduce a novel sparsification approach that combines attention scores with spectral cues derived from the frequency content of token embeddings. Our experiments show that frequency-aware app

ALT While arousal can be reliably predicted from musical audio, emotional valence remains difficult to model due to its subjective and context-dependent nature. In this work, we investigate the potential of in-context learning (ICL) with large language models to advance continuous valence and arousal prediction. Rather than predicting emotion scores directly, our framework leverages contextual demonstrations from an auxiliary dataset to refine the initial predictions produced by a small, task-specific base model. We systematically evaluate a text-based ICL variant using lyrics and generated audio captions, alongside a multimodal variant that incorporates raw audio signals. Using the entire MER60 dataset strictly as a held-out test set, our experiments demonstrate substantial performance gains, particularly for valence. Text-based ICL improves the valence R² from 0.110 to 0.427 with 80 demonstration shots, while the multimodal variant achieves 0.346 with only 10 shots. These findings sugges

ALT In standard acoustic anomaly detection (ASD), models are usually trained separately for each machine or domain using explicit metadata. However, in realistic deployments, machine identifiers are incomplete, unreliable, or simply unavailable. Thus, metadata-free machinery ASD asks a single model to monitor mixed machine populations without machine IDs. In this paper, we argue that the main failure mode is not a weak detector family, but representation entanglement. The heterogeneous normal modes overlap in frozen pre-trained feature spaces, making anomaly scoring and approximate retrieval unreliable. We study this problem directly and propose HARMONY (Hierarchical Anchor Retrieval on Manifold for Oblivious-source acoustic aNomalY detection), an anchor-guided geometric repartitioning framework that reorganizes mixed-source features into compact Voronoi regions and reuses this structure for hierarchical retrieval. On DCASE 2020, HARMONY improves mean AUC from 75.40% to 90.00% (14.60 perce

ALT Text-to-music alignment is commonly evaluated by the global similarity between text and audio embeddings, which collapses all described attributes into a single score and obscures which ones are missing. We instead introduce MQAScore, which verifies each atomic musical concept along five clip-level dimensions (genre, instrument, mood/theme, vocal, and usage) by the probability that a large audio language model (LALM) answers affirmatively to a binary question. To assess evaluator reliability, we construct verification labels from presence/absence annotations and LLM-guided concept substitutions, and propose the Sensitivity-Invariance Ratio, which measures how selectively an evaluator responds to meaning-changing substitutions. Experiments show that concept-level scoring improves both question-answering and similarity-based evaluators, and MQAScore can be a more reliable and interpretable fine-grained complement to global similarity for evaluating text-to-music alignment.

ALT Self-supervised learning (SSL) representations are widely used in speech restoration (SR), and the prevailing trend is SSL feature cleansing: fine-tuning the SSL to recover clean features from degraded speech, then conditioning the restoration model on them. However, the representational capability of SSL when encoding degraded speech has been underexplored, and we ask whether cleansing always benefits SR training. Across SSL encoders and perceptual quality proxies, we discover perceptual correlation collapse—under severe degradation, cleansing degraded SSL features toward clean ones misaligns with the SR objective. We hypothesize the restoration backbone can supply the SSL with clues to resolve this collapse, since its intermediate layers already produce partially restored features. We therefore propose Early Restoration Injection (ERI), which routes intermediate features from the restoration backbone into the SSL through a lightweight conditioning network. ERI excels over the uncondi

ALT Mixing requires not only applying processing but also assessing the resulting mix. Audio-language models can provide conversa- tional mixing advice, but existing evaluations do not separately test whether they can judge specific mixing issues. Since professional supervision for such judgments is scarce, we construct a curriculum of 11 vocal-mix issues at multiple severity levels and use it to train MixJudge, a language-queryable audio critic. MixJudge shows its ability to retrieve mixing issues, distinguish opposite issues, and order the severity of an issue. Moreover, its judgments transfer to menu selection: given a set of processing candidates, MixJudge often favors versions acoustically closer to a held-out professional version, demonstrating how explicit mixing judgment can support comparison and downstream mixing decisions.

ALT Controlling emotional intensity remains challenging in expressive text-to-speech synthesis, particularly when emotion must be inferred without explicit labels. We propose EmoFI-TTS, a face-conditioned framework that derives emotion category and intensity from a single facial image while extracting speaker characteristics from reference audio. Modality-specific representations are fused to condition a pretrained speech synthesizer, with cross-speaker training encouraging separation of affect and vocal identity. An intensity-conditioned refinement module enhances the generated mel-spectrogram, while interpolation of learned intensity embeddings enables continuous control without additional training. On speaker-disjoint MEAD evaluation, EmoFI-TTS achieves on average 64.4% and 75.2% objective and subjective emotion intensity accuracies, while retaining low word error rate and high naturalness.

ALT Most voice-cloning systems are built for audio alone: they copy the reference recording's delivery and acoustics, so a voice cloned on a phone sounds like a phone recording whether the speaker is pictured in a studio, on a street, or in a cathedral. Speech for a talking video should sound like the pictured person speaking in the pictured place. We present HeyGen Voice, a scene-aware voice-cloning model that separates who is speaking from how and where: it keeps the speaker's voice from an everyday recording while the target image sets the delivery and acoustics. Prior image-conditioned TTS does half of this job: it either adds scene acoustics without keeping a specific speaker or infers a voice from a face. HeyGen Voice is a multimodal autoregressive transformer conditioned on the image, speaker and scene captions, and the voice recording, trained in five stages that move from multilingual TTS pretraining through simulated and real cross-scene adaptation to reinforcement and preference

ALT LLM correctors of ASR output are judged by aggregate WER, which hides what they fix and what they break. We decompose every WER change exactly into repaired tokens, damaged tokens and insertions, and use this to ask what the source audio adds to a corrector. We compare correction with and without the audio, for the model's own draft and for the output of an independent recogniser, on three corpora. With Gemini 2.5 Flash, text-only correction of its own draft breaks 13-32% of already-correct transcripts; with the audio, 1-3%. Damage falls in both settings. Repair falls against the own draft and rises against the recogniser. On medical dictation, kept insertions cancel the gain in net WER. The open-weight Voxtral, which rarely edits, does not show this pattern. Prompts differ between the two arms, so the contrasts bound the effect of the audio and do not isolate it.