Sperm-whale codas are usually described by the number and timing of their clicks. Earlier acoustic studies showed that individual clicks and longer coda sequences contain additional organization. We ask how that organization compares with music, whose smaller sounds also form larger units and ordered sequences. We compare codas with performed violin music, drum grooves, and sung melodies. Their sequences resemble music in some measures of predictability, yet codas show a different relationship between the smaller sounds within a unit and the order of units across a sequence. This combination was not observed in the musical references tested. Coda timing also varies coherently and carries information about individual callers. The recordings show another striking property: broad, reproducible variation along acoustic dimensions associated with human ratings of emotion, with a range comparable to human audio in most eligible tests. These findings motivate an acoustic blueprint that describes natural codas beyond their click timing. Its importance is apparent in synthetic audio: WhAM produces recognizable coda-like recordings, yet the tested clips remain distinguishable from natural codas in five of six acoustic comparisons after strict matching. The blueprint provides a fuller way to study natural codas and to evaluate how faithfully synthetic recordings represent them.
https://arxiv.org/abs/2610.33974
Automatic DJ systems mostly target electronic dance music, whose regular structure makes rule-based mixing relatively easier. Vocal-rich popular music is harder: which track to play next, where to cue it, and which transition to use are tied together, so fixed rules handle them poorly. We present DJustify, a pop AI-DJ that puts an LLM in a reason--propose--verify--repair loop and lets it choose the next track, cue points, and mixing technique together. The LLM samples several transition plans; an external acoustic checker then scores the rendered audio and triggers repair when a check fails. Sampling keeps several candidate transitions per track pair instead of one fixed mix. In blind listening tests our transitions beat Mosaikbox, a reimplemented crossfade, and a cue baseline that reuses the crossfade's cues; that last comparison shows most of the margin comes from cue placement. The same planner also picks and orders a set along an emotion arc: this improves story coherence over a no-story ablation, and within a set story and transition ratings show no measurable gap from a human DJ. The checker mainly adds reliability, not higher average quality: it repairs rare but audible errors such as cut vocals, while the planner stays non-deterministic.
https://arxiv.org/abs/2610.33434
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 recording, preserving the weakly-supervised nature of NyTT. Experimental results on VoiceBank-DEMAND and CHiME-3 real recordings demonstrate the efficacy of the proposed combination.
https://arxiv.org/abs/2610.32870
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-frequency separation in a single encoder--decoder pass. We train Falcon with an encoder-space speaker contrastive loss. This loss suppresses near-field leakage at zero inference cost and transfers across backbones. Falcon achieves state-of-the-art extraction quality on RealSSA-Sim, LRS2-2Mix, LRS3-2Mix, and VoxCeleb2-2Mix. Compared with the causal AV-TFGridNet baseline, it cuts parameters by 91.9%, computation by 20.2 times, and GPU inference latency by 11.1 times. Code and demo are available at this https URL.
https://arxiv.org/abs/2610.32749
Full-duplex speech models can listen and speak at the same time, enabling natural, low-latency interaction. In counseling, however, these models often focus on the latest utterance and lose track of the seeker's underlying problem. We call this failure Stressor Blindness. We propose CounselPlex, a stressor-aware full-duplex framework that uses two operations. CounselPlex updates a short stressor state during seeker silence and injects this state into <PAD> positions while listening. We also introduce RoPE Position Shift Augmentation (RPSA), which broadens positional coverage during training and improves performance at longer turn depths in our evaluation. LLM-judge evaluations show improved counseling quality and stressor grounding over strong baselines.
https://arxiv.org/abs/2610.32702
Full-duplex speech models listen and speak at the same time, which makes them promising for natural, open-ended conversation. But can they sustain a coherent conversation for tens of minutes? Because they generate a token every frame, even while listening, they exhaust their context windows within minutes. Yet existing benchmarks evaluate only single turns or a few conversational rounds, too short to expose the long-horizon problem. We introduce the Full-Duplex Long-Horizon Benchmark (FD-LHB), which tests five recent full-duplex models on long replayed conversations and in live conversation with an LLM partner. Every evaluated model eventually either degrades or exhausts its context. Models that keep the full history often degrade before their context runs out, while sliding-window models still fall into repetition, silence, and gibberish. For sliding-window models, we identify two contributing mechanisms. Gibberish and silence are linked to Initialization-Anchor Eviction, where the sliding window discards the first KV entry. Repetition is also reinforced by the model's own recent outputs. Guided by this diagnosis, we apply two simple fixes: Initialization-Anchor Pinning (IAP) keeps that first entry, and Duplex Repetition Penalty (DRP) discourages echoing while guarding against prolonged silence. Together, they support the diagnosis and, without retraining, substantially reduce conversational collapse in replays of up to an hour while running in real time.
https://arxiv.org/abs/2610.32349
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, electric drive load, vehicle speed, and auxiliary-drive speed. Since isolated real-world reference stems are costly to obtain, the model is trained on a physics-based parametric data generator that synthesizes labeled component sounds from randomized virtual-vehicle hardware configurations and driving scenarios, so that the ground-truth contribution of each source is known by construction. Validation on both synthetic and measured vehicle interior sounds probes the achieved separation performance and underscores the feasibility of applying the proposed method for acoustic contribution analysis in technical systems.
https://arxiv.org/abs/2610.32310
We propose DIAL-S2ST, a post-training method for learning inference-time latency control in simultaneous speech-to-speech translation models. Our approach reuses pretrained translation capabilities through self-distillation from lookahead predictions, while limiting the influence of large text distillation losses to account for the imitation gap. This provides supervision for earlier emission without paired target data or reward computation. To make the learned timing adjustable at inference, we jointly train a single LoRA adapter across scales with matched lookahead guidance. Experiments on French-to-English translation with Hibiki demonstrate that only 10 hours of source speech enable this adaptation, providing flexible latency control with a favorable quality-latency trade-off.
https://arxiv.org/abs/2610.32214
Live pitch displays, score followers and accompaniment systems must know which pitches are sounding within tens of milliseconds, but instrument-agnostic multi-pitch estimation (MPE) has mainly been designed and evaluated offline. We present JIT-MPE, a causal MPE model of 86k parameters for mixed ensembles. It gives an immediate estimate of each 20 ms frame and re-estimates the same frame as 20, 40, 80 and 160 ms of further audio arrive, so that a live display can show pitches at once and then refine them. We score each output only at a deadline by which it can be computed from the audio that has arrived, on five development sets and four held-out sets evaluated only after all design choices were frozen. At a 50 ms deadline, which reads the update made with 40 ms of lookahead, JIT-MPE is significantly more accurate than five of six published offline MPE systems in 38 of 45 comparisons (15 of 20 on the held-out sets) and less accurate in only two, although these systems read the whole recording and all but one have 6 to 170 times as many parameters; the sixth, supervised on URMP, is higher on four of the nine sets. The deadline costs little: on the held-out sets, JIT-MPE at 50 ms is within $-1.27$ to $+0.60$ points of recording-level macro F1 of its own final output with 160 ms of lookahead and within $-2.08$ to $+0.79$ points of a bidirectional model of similar size. Waiting pays off where the immediate estimate is weakest: the update at 50 ms adds 1.7-3.6 points over it on the development data and three of the four held-out sets, and raises the recall of reference frames in the first 20 ms after a note onset from 9.8% to 38.4% on the held-out AAM set. The slowest measured frame takes at most 4.15 ms on one CPU thread. Code and trained weights are available at this https URL.
https://arxiv.org/abs/2610.33113
Recent advances in speech generation are shifting toward context-aware, multi-turn, and multi-speaker synthesis. While these capabilities are in high demand for applications such as audiobook and audio drama production, evaluation has not kept pace with these advances. Beyond traditional zero-shot Text-to-Speech (TTS), modern systems in this domain primarily fall into three categories: instruction-controllable generation models, multi-turn dialogue models, and the audio branches of audio-visual generation models. However, existing benchmarks evaluate these paradigms in isolation, failing to provide a unified assessment of context modeling, instruction following, and multi-speaker generation. Meanwhile, recent progress in audio understanding models has made it feasible to evaluate such complex scenarios using LLM-as-a-Judge approaches. To bridge this gap, we introduce DRAMA-Eval, a comprehensive benchmark for evaluating such systems. DRAMA-Eval utilizes structured script contexts and offers a holistic evaluation framework covering objective, local, and global aspects of generation quality, enabling the assessment of acoustic fidelity, sentence-level execution, and long-range coherence. We benchmark leading open-source and commercial models on a human?verified dataset. The results reveal critical weaknesses in long-range speaker consistency and implicit instruction following that require deep contextual understanding. To facilitate reproducible research, we release a 12-hour bilingual (Chinese-English) test set of manually corrected real-world scripts, accompanied by ground-truth audio, evaluation code, and benchmark results.
https://arxiv.org/abs/2610.31796
We introduce Piano2Pop, a music-expansion task that transforms piano MIDI into instrumental pop productions. Enabled by recent advances in music generation and polyphonic music transcription, our pseudo-supervised approach conditions a pretrained flow-matching model on piano rolls without aligned piano-pop supervision. We train on synthetic piano-instrumental pairs derived from pop recordings, comparing pair-free transcription, including function-selective (FST) and register-density (RDA) augmentations, with a pair-supervised piano-cover generator as pseudo-demo sources. On 476 testing real-world piano-cover/pop pairs, the pair-supervised approach achieves the best Frechet Audio Distance, Accompaniment Prompt Adherence, and spectral shape on real-piano inputs, while FST mitigates piano-heavy outputs in pair-free training and remains a promising alternative. All fine-tuned systems significantly outperform the zero-shot baselines, which suggests a role for task-specific modeling.
https://arxiv.org/abs/2610.31510
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-frequency and fine-frequency representations. These tokens are combined with environmental priors and fed into a pretrained large language model (LLM) that evaluates target-present and noise-only hypotheses and generates a structured detection report detailing target presence, bearing, spectral-line locations, received SNR, range, and per-field confidence scores. A physics-parameterized data engine extended to realistic oceanic channels provides traceable supervision at both discrete-label and structured-description levels. Experiments under white-noise and mixed ocean-background conditions demonstrate reliable detection, accurate bearing estimation, and physically interpretable structured reports, validating the feasibility of evidence-grounded underwater acoustic detection.
https://arxiv.org/abs/2610.31346
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.
https://arxiv.org/abs/2610.31252
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 approaches, particularly those based on spectral flatness and low-frequency energy, consistently outperform attention-only methods. We also find that sparsification based on spectrogram patch intensity is especially effective for longer audio inputs. These results highlight the value of incorporating frequency-domain and input-specific information into sparsification strategies to enhance performance in audio tasks.
https://arxiv.org/abs/2610.31235
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 percentage points) over the strongest unified baseline and from 83.90% to 90.00% over a strong foundation-feature baseline. On a single CPU, its hierarchical retrieval achieves a 7.8x speedup over exhaustive search with only a 0.20 percentage-point AUC drop. These results suggest that incorporating explicit geometric partitioning can improve both detection accuracy and retrieval efficiency for ASD. Code is available at this https URL.
https://arxiv.org/abs/2610.31093
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.
https://arxiv.org/abs/2610.31083
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 unconditioned baseline and, on the VoiceFixer benchmark, achieves competitive performance among multiple baselines.
https://arxiv.org/abs/2610.30869
This study develops an audio-visual emotion recognition system that integrates automatic utterance segmentation with multimodal fusion. Unlike conventional methods that rely on manually annotated utterance boundaries, the proposed system automatically generates candidate segments from continuous dialogue and extracts the corresponding audio and visual features for emotion classification. To address the challenges introduced by automatic segmentation, the proposed AGF-Net integrates Audio-Guided Fusion (AGF), Multimodal Negative Learning (MNL), and Predictive Dynamic Fusion (PDF) to improve cross-modal fusion, modality balance, and robustness to varying modality quality. Experimental results show that AGF-Net achieves 64.92% Accuracy and 65.47% F1-score under clean conditions, 62.13% Accuracy and 63.08% F1-score under moderate noise, and 58.19% Accuracy and 59.41% F1-score under higher noise. Overall, the proposed framework reduces reliance on manually annotated utterance boundaries and maintains competitive performance under automatically segmented and noisy audio-visual inputs.
https://arxiv.org/abs/2610.30651
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.
https://arxiv.org/abs/2610.30477
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 optimization. Two clone policies trade scene adaptation against fidelity to the original recording, and an audio anchor holds long scripts in one voice and one acoustic environment. Listeners prefer HeyGen Voice over leading commercial systems across a third-party arena, production votes, and talking-video studies: it ranks first (Elo 1201) on the public Artificial Analysis controlled-voice TTS leaderboard (October 2026); in a blind test, users cloning their own voice chose it over ElevenLabs v4 and Cartesia Sonic 3.6 in 62% and 54% of votes; and volunteers rated talking videos of their own digital twin about 10 to 30 points higher (out of 100) when voiced by HeyGen Voice than by leading commercial alternatives. Try HeyGen Voice and hear samples at this https URL.
https://arxiv.org/abs/2610.30470