SEARCH · Search arXiv

Results for “cs.SD”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

7,800 records · Page 6Linked to original sources

arXiv2026

AudioKV: KV Cache Eviction in Efficient Large Audio Language Models

Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-context inference. While general KV cache compression techniques excel in LLMs, they often fail in the audio domain by overlooking the intrinsic temporal continuity of acoustic signals. To bridge this gap, we propose AudioKV, a novel framework that robustly prioritizes audio-critical attention heads through a hardware-friendly semantic-acoustic alignment mechanism. Specifically, we identify these modality-specialized heads by analyzing attention scores in ASR tasks and dynamically allocate KV cache budgets preferentially to them. Furthermore, we introduce Spectral Score Smoothing (SSS), an FFT-based global filtering strategy designed to suppress high-frequency noise and recover smooth global trends from importance scores, ensuring more balanced token selection with unprecedented precision. Extensive evaluations across multiple LALMs, including Qwen and Gemma series, demonstrate that AudioKV significantly outperforms baselines while enhancing computational efficiency. Notably, at a 40% compression ratio, AudioKV maintains near-full accuracy on Qwen3-Omni-30B with only a 0.45% drop, whereas traditional methods suffer from catastrophic performance degradation and repetition. Our code will be released after acceptance.

cs.SD↗

arXiv2026

From local kernels to global form: modeling the emergence of musical content

Markov models are established tools for symbolic music, including non-homogeneous formulations. The narrower contribution examined here is an observation-driven estimation mechanism: overlapping sliding windows derive a trajectory of local transition kernels from one symbolic sequence rather than from an exogenous formal partition. We test this mechanism on 273 logical note events from Debussy's Syrinx (1913), using the often-proposed A-B-A' reading as a reference rather than ground truth. We apply the same validation to absolute-pitch and notated-duration kernels. At $L=6$, both reference boundaries attain the Jensen--Shannon maximum in both dimensions; the duration plateau is substantially narrower (64 of 267 comparisons) than the pitch plateau (210 of 267). Because the theoretical maximum for consecutive sliding-window comparisons is set by window geometry and equals $1/\sqrt{L-1}$ for maximal turnover of the entering/leaving transition, the pitch value at $L=6$ and its broad plateau are not, by themselves, strong evidence. Their cross-dimensional alignment is consistent with boundary sensitivity, while the broad plateaus preclude treating either curve alone as a unique automatic segmenter. Five-hundred-draw re-synthesis experiments quantify departure from the source in both dimensions and expose an exact-copy degeneracy at $L=2$.

cs.CL↗

arXiv2026

Removing Speech, Keeping Activities: A Privacy Firewall for Acoustic Sensing in Assisted Living

Acoustic sensing offers a promising non-intrusive approach for monitoring daily activities of older adults, yet speech privacy concerns remain a critical barrier to real-world deployment. We present a privacy firewall pipeline based on a U-Net encoder-decoder, trained entirely on synthetic data, that removes speech from ambient audio while preserving environmental sounds indicative of daily activities. Activity recognition is performed using VGGish transfer learning with an SVM classifier. Evaluated on the ESC-50 and SINS datasets across multiple speech content levels, the proposed model reduced residual speech to 0% VAD-detectable speech (Silero Voice Activity Detection) under all tested conditions, outperforming Facebook Denoiser (6.55% residual), SepFormer (36.34%) and ConvTasNet (47.21%) on ESC-50 at the 100\% speech level. On ESC-50 at 40% speech level, classification performance recovers to 85% precision and 85% recall after speech removal, compared with 81%/75% before removal and an 84%/83% speech-free baseline. Evaluation on real-world participant home recordings collected with the AudioHive app showed 0% VAD-detectable speech after processing while maintaining 76% precision and recall. The pipeline enables privacy-preserving acoustic sensing without sacrificing activity recognition performance, addressing a key obstacle to the adoption of ambient monitoring in elderly care.

cs.SD↗

arXiv2026

WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs

Long-form audio inputs make the KV cache the dominant memory cost of speech LLMs. Prefill-only KV compression methods permanently discard audio KV positions once evicted, with no pathway to recover them during decoding. We show this is fragile on long-form audio: prefill attention concentrates near the audio start (an attention-sink effect), while decode-time attention distributes broadly, and the two rankings overlap weakly. We propose WnW (Waxing-and-Waning KV cache), which classifies KV-heads into anchor, tidal, and fixed roles via offline calibration. Anchor heads keep all audio KV on GPU and yield a decode-time signal of which audio region each token is read from; tidal heads keep a CPU-resident complement that is recalled chunk-by-chunk based on aggregated anchor-head scores; fixed heads keep only an on-GPU subset, with the rest permanently discarded. On LibriSpeech-Long with two 3B backbones (Voxtral-mini-3b and Qwen2.5-Omni-3B), WnW preserves near-Full-Cache accuracy while keeping only 20% of audio tokens on GPU, where prefill-only baselines fail to terminate. Results generalize across language, task, and domain shifts, and CPU-GPU recall adds little decode-time overhead in our measurements.

cs.CL↗

arXiv2026

SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds

As generative audio models grow in complexity, the computational and ecological costs of synthesizing everyday sounds have become increasingly prohibitive, often requiring industrial-scale resources and massive datasets. In this paper, we present SCAPES: a Semantically Conditioned Autoregressive Prior for Environmental Sounds. SCAPES is a lightweight, resource-efficient generative model designed to synthesize high-fidelity environmental textures through high-level semantic control. By operating on the continuous latent manifold of a neural audio codec, our approach bypasses the rigid structural constraints inherent to discrete tokenization. We propose a segmentation strategy that decomposes audio into overlapping segments, enabling a Continuous Normalizing Flow (CNF) to model the evolution of latent trajectories using Flow Matching. Our experiments demonstrate that a 36-million parameter instance of SCAPES can be trained on limited, uncurated datasets using a single consumer-grade GPU. Notably, convergence is achieved after training for approximately twice the source audio duration, yielding high-fidelity outputs with robust long-term stability and semantic consistency. Furthermore, we showcase the model's capacity for smooth semantic interpolation, providing a flexible and accessible tool for open research and creative sound design. Code, pretrained weights, audio examples, and an interactive demo are publicly available on our project page https://cordutie.github.io/projects/scapes.html

cs.SD↗

arXiv2026

Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions

Neural audio codecs (NACs) convert speech into discrete token sequences, and prior work has reported that these sequences follow language-like statistical laws. This paper analyzes the token statistics of 13 NACs spanning multi-codebook residual vector quantization (RVQ), single-codebook VQ, and non-VQ designs, evaluated on three corpora under clean, white-noise, and real-world DEMAND-noise conditions. Zipf and Heaps parameters, unigram entropy, codebook occupancy, and Jensen-Shannon divergence (JSD) are estimated from matched token samples with explicit fit-validity safeguards and family-conditional $n$-gram orders. Corpus identity explains little variance in any metric, whereas acoustic condition and quantizer meta-category dominate in a metric-dependent way, and unigram entropy is the metric most strongly associated with meta-category. Clean-to-noise JSD computed at a common unigram order is associated with mel-cepstral distortion most clearly under DEMAND noise. The collapse and explosion degradation signatures previously reported for RVQ codecs concentrate in RVQ cells under white and DEMAND noise, respectively; explosion also occurs in non-VQ codecs, and single-codebook VQ codecs shift in occupancy and distribution shape without either signature. These results provide architecture-conditioned conventions for applying language-statistical analysis to NAC tokens.

cs.CL↗

arXiv2026

Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection

Speech-based Alzheimer's disease (AD) detection increasingly relies on speech-enhanced and curated versions of the Pitt Corpus, where speech enhancement, sample selection, and demographic balancing are often treated as beneficial preprocessing steps. However, whether these transformations improve real-world AD detection or instead affect model generalization and prediction behavior remains unclear. In this work, we revisit the role of speech preprocessing and dataset curation across widely used benchmarks for speech-based AD detection. We evaluate the speech quality of different datasets, the cross-dataset generalization of multiple deep learning models under matched and mismatched enhancement settings, and the behavior of several recent large audio-language models (LALMs). Experimental results show that across multiple supervised speech models, speech-enhanced datasets often improve in-domain performance while reducing robustness in cross-domain evaluation. Matched enhancement between training and test data alleviates, but does not eliminate, this degradation. LALMs show a similar sensitivity: enhanced datasets induce stronger class imbalance and prediction shifts than unprocessed data. These results suggest that speech preprocessing and dataset curation can substantially influence downstream AD detection behavior, indicating that ``cleaner'' speech datasets are not necessarily more reliable for real-world AD detection.

cs.SD↗

arXiv2026

Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition

Modern automatic speech recognition (ASR) scenarios require both spoken-form transcripts for faithful transcription and readable written-form transcripts with inverse text normalization (ITN). However, these forms are typically produced by cascaded modules, where a spoken-form ASR output is rewritten by a separate ITN component, making written-form ASR-ITN vulnerable to recognition errors and decoupling normalization from acoustic-contextual modeling, especially for semantically dependent numeric expressions. In this paper, we propose Dual-Form ASR (DF-ASR), a framework that extends spoken-form ASR capability to semantics-aware written-form ITN through paired spoken-form and written-form supervision while retaining prompt-level selection between transcript forms. The dual-form supervision is constructed via a large language model (LLM)-driven generate-and-judge workflow, and training is further enhanced by ITN-MWER, a sequence-level objective that assigns higher cost to errors on normalization-sensitive spans. We also introduce a decision-aware REQUIRE-ITN/\FORBID-ITN protocol to separately measure required normalization and forbidden-span preservation. On manually annotated Chinese subsets from SpeechIO, DF-ASR consistently outperforms open-source ASR-ITN systems, remains competitive with strong closed-source references, and preserves reliable prompt-level control between spoken-form and written-form outputs.

cs.CL↗

arXiv2026

Arbitrary Polygon Oscillator: Generalizing Polygonal Synthesis to Arbitrary Shapes, Morphing, and Three-Dimensional Polyhedra

Polygonal synthesis generates audio by traversing the perimeter of a polygon with a phasor; prior work uses a constant angular velocity, whereas the proposed system adopts constant arc-length (perimeter) velocity. Existing formulations operate on regular, parametrically defined polygons, producing smooth timbral transitions within a single family of shapes. This paper generalizes polygonal synthesis around a unified arc-length engine: vertex data of any origin feed the same DSP pipeline. First, we adapt the oscillator to accept arbitrary vertex configurations from an external buffer, opening the possibility for a broad class of closed polygons -- regular, irregular, or star-shaped -- to function as a waveform generator. Second, a hybrid interpolation algorithm enables smooth morphing between polygons with unequal vertex counts, passing through intermediate shapes that have no parametric description. Third, we extend the paradigm to three dimensions: a convex polyhedron rotated about three axes is sliced by a fixed horizontal plane, and the resulting cross-section yields a continuously variable polygon controlled by the solid's orientation. The system runs in RNBO (Cycling~'74) with a geometry caching strategy that avoids per-sample recomputation. Antialiasing combines a four-point polyBLAMP correction derived from runtime Bézier tangents with adaptive oversampling, adapting the correction geometrically to general vertex configurations without per-shape analytical derivation.

cs.SD↗

arXiv2026

MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries

Dominant audio classification pipelines rely either on compact handcrafted summaries or on fixed time-frequency frontends such as log-mel representations prior to deep modeling. While highly successful, these representations do not explicitly expose the physical dynamics of the underlying sound-generating event. We introduce MADS (Multi-view Acoustic Descriptor Set), a compact 19-dimensional physics-informed descriptor set de- signed to capture complementary spectral, temporal, mechanical, and stochastic structure in audio signals. Rather than treating sound only as a spectral pattern, MADS encodes properties related to excitation, damping, periodicity, impulsiveness, and structural consistency within a unified multi-view representation. We evaluate MADS using standard classical machine learning models on ESC-10, ESC-50, and MSoS, and compare it against two conventional handcrafted baselines: a compact 26D MFCC- based baseline and an expanded 38D spectral-summary baseline. Across ESC-10 and ESC-50, MADS achieves the strongest peak results overall, reaching 81.00% and 52.78%, respectively, while using roughly half the dimensionality of the 38D baseline. On MSoS, MADS again delivers the strongest top-end performance, reaching 67.48%. These results establish MADS not merely as a competitive standalone descriptor set, but as the foundational descriptor layer of a broader acoustically grounded representation program for future frame-level and deep-learning-compatible audio modeling.

cs.SD↗

arXiv2026

Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness

Smooth speaker transitions are fundamental to effective conversation and rely on an interlocutor's ability to predict when to enter the conversation. This ability depends on accurately interpreting and expressing the verbal and non-verbal cues that signal when a speaker wishes to take or relinquish the floor. The process becomes even more complex in noisy, natural, multi-party settings, with multiple interlocutors available. This study models how gaze and speech, together with perceived interpersonal closeness, signal conversational floor changes in free four-person dialogue. Using the GaMMA corpus, we trained logistic regression models using interpretable, behaviourally motivated features extracted before each turn-taking event to classify floor-transfer outcomes as gaps or overlaps. Predictors included gaze features such as transition motifs and behavioural contrasts, entropy, gaze-based addressee identity, and mutual gaze, alongside speech features derived from speaker loudness, as well as perceived interpersonal closeness (IOS) between speakers. Results show that gaze features capture predictive structure, and that combining them with loudness improves performance (ROC AUC = 0.76 +- 0.04). Loudness reflected speaker control, while gaze dispersion and addressing indexed listener readiness and competitive entry. Performance remained robust across noise conditions, indicating that gaze provides a complementary, noise-resilient cue to turn-taking dynamics.

cs.CL↗

arXiv2026

Perceptible or Not? Diagnosing Passive Fingerprints for Speech Deepfake Attribution

Passive fingerprints (intrinsic traces naturally left by generators) have been shown to enable attribution in speech deepfake detection, yet their persistence, reproducibility, and content-independence remain unverified. Moreover, no prior work distinguishes perceptible from imperceptible fingerprints, although the two have very different implications for attribution reliability. Perceptible fingerprints, such as emotional expression, are shaped by perceptual quality objectives and may change across model updates, whereas imperceptible fingerprints are not explicitly optimised by current training objectives and are rarely considered in existing dataset design or training strategies, as they have limited influence on downstream applications. We therefore propose a Perceptible-Imperceptible Passive-fingerprint Diagnostic Protocol (PIPDP) to define and separately analyze these two fingerprint types. PIPDP comprises three complementary analyses: multi-evidence fingerprint verification through residual-energy, reproducibility, and saliency analyses, perceptually transparent perturbations preserving audio quality, and prompt-driven emotion change that modifies perceptible fingerprints without model retraining. Experiments across ten speech generators and three attribution detectors show that imperceptible fingerprints provide persistent attribution cues. Perceptually transparent perturbations reduce attribution accuracy by up to 48.2\% on HiggsAudioV3, whereas emotion-driven changes leave attribution largely unchanged, with only about a 1.0\% accuracy variation across emotions on CosyVoice2 using w2v-bert-MLP. These results suggest that imperceptible fingerprints are more reliable for trustworthy attribution.

cs.SD↗

arXiv2026

VocalAffectBench: Evaluating Vocal Emotion Recognition in AI Audio Models

Voice products increasingly need affective cues that are present in speech but absent from transcripts. We introduce VocalAffectBench, a public, test-only benchmark for evaluating whether AI audio models can identify expressed vocal emotion from raw audio. The benchmark contains 273 human-recorded English WAV clips from 51 speaker accounts totaling 1.95 hours across seven labels: angry, disgusted, fearful, happy, neutral, sad, and surprised, with 39 clips per class. All baselines are evaluated from audio alone, without transcripts or contextual metadata. Across six released baselines, average accuracy is 35.5%. The strongest baseline, gemini_3_5_flash, reaches 46.5% on the seven-way task, above the 14.3% random baseline but far from robust emotion recognition. A secondary valence-bucket analysis maps labels into positive, neutral, and negative classes, excluding surprised because its valence is ambiguous. Aggregate accuracy under this coarser view is 50.9%. Performance is highly uneven across classes. By recall, neutral is identified most reliably at 75.6% averaged across baselines, while surprised and fearful reach only 10.7% and 15.4%, respectively. These results show that the evaluated baselines can extract some affective signal from speech, but discrete expressed-emotion recognition remains fragile, especially for non-neutral emotions that are often most important in voice agent workflows.

cs.CL↗

arXiv2026

Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models

Audio language models are designed to understand speech, yet it remains unclear whether they capture how something is said beyond what is said. We present a mechanistic analysis of paralinguistic information in four open source models, Whisper-large-v2, Qwen2-Audio-7B Instruct, Qwen2.5-Omni-7B, and Chroma-4B, using the Expresso dataset with controlled speaking styles. We combine centered kernel alignment, linear probing with leave one speaker out evaluation, open ended tone prediction, and a content prosody leakage metric to trace how style information moves from the audio encoder to the final output. All models strongly encode speaking style in the late encoder, that is, the top third of the audio encoder's layers, but this information is consistently degraded before reaching the output. The projector reshapes representation geometry without removing information, while decoders differ in how much style they preserve depending on architecture and training objective. At the output level, models fall into two behaviors. Some are content driven, where predictions depend mainly on text. Others are acoustic driven, where predictions vary with speaking style. The leakage metric quantifies this difference, and qualitative results confirm it. Overall, we identify a gap between what models encode and what they use, highlighting a key limitation in current audio language models.

cs.SD↗

arXiv2026

UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models

Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream approach. However, most current approaches address these tasks separately rather than through a unified framework. This work aims to integrate these two tasks into one unified model. Although discrete speech tokenization enables joint modeling, its inherent information loss limits performance in both recognition and generation. In this work, we present UniVoice, a unified LLM framework through continuous representations that seamlessly integrates speech recognition and synthesis within a single model. Our approach combines the strengths of autoregressive modeling for speech recognition with flow matching for high-quality generation. To mitigate the inherent divergence between autoregressive and flow-matching models, we further design a dual attention mechanism, which switches between a causal mask for recognition and a bidirectional attention mask for synthesis. Furthermore, the proposed text-prefix-conditioned speech infilling method enables high-fidelity zero-shot voice cloning. Experimental results demonstrate that our method can achieve or exceed current single-task modeling methods in both ASR and zero-shot TTS tasks. This work explores new possibilities for end-to-end speech understanding and generation. Code is available at https://github.com/gwh22/UniVoice.

eess.AS↗

arXiv2026

CAD: Conflict-Aware Decoding to Mitigate Cross-Modal Hallucinations in Omnimodal Large Language Models

Omnimodal large language models (Omni-LLMs) integrate audio, video, and text, yet remain vulnerable to cross-modal hallucinations, where one modality improperly influences predictions about another. Existing training-free decoders modulate modality influence through perturbation or relevance weighting, but do not assess predictive compatibility within the joint audio-visual branch. Because joint-branch discrepancies may indicate either harmful interference or useful complementarity, reliable intervention requires assessing both discrepancy magnitude and actionability. To this end, we propose Conflict-Aware Decoding (CAD), a training-free framework comprising Potential Conflict Magnitude Estimation (PCME) and Conflict Actionability Assessment (CAA). PCME quantifies potential conflict using audio-video disagreement and the deviation of the joint prediction from a relevance-weighted unimodal reference. CAA then applies Dempster-Shafer reliability discounting to task-space answer relations, using query relevance and answer decisiveness to determine whether intervention is warranted. When an actionable conflict is identified, CAD selectively reallocates decoding weight from the joint branch to the unimodal branches. Experiments on CMM, AVHBench, WorldSense, and VideoMME show that CAD consistently outperforms the base decoder and competitive training-free methods across multiple audio-visual backbones. On Qwen2.5-Omni-7B, CAD improves overall accuracy by 14.1 and 8.0 percentage points on CMM and AVHBench, respectively, without model retraining.

eess.AS↗

arXiv2026

Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTS

Natural-language instructions enable flexible control of synthesized speech, yet emotional TTS systems primarily model a single utterance-level affect, leaving multi-emotion control underexplored. We study two complementary multi-emotion TTS tasks: emotion trajectory, which spans several ordered affective stages, and emotion blending, in which multiple emotions coexist throughout an utterance. These tasks expose a supervision mismatch: supervised fine-tuning (SFT) does not explicitly evaluate emotion features, while single-emotion rewards provide neither structure-aware feedback for trajectory completion nor pair-aware feedback for blending. We introduce HybridEmo, a post-training framework that initializes both tasks with SFT and then aligns the speech-token policy through Group Relative Policy Optimization using a sample-aware hybrid reward. For trajectory samples, segment-aligned consistency combines average and weakest-stage evidence to preserve the correctness and completeness of prescribed stages. For blending samples, a GMM-based reward combines frame-level support from the union of target-emotion anchors in an offline emotion space with an utterance-level weaker-target margin. Both branches share an ASR reward and are routed within a unified policy. On MultiEmo-Test, HybridEmo significantly improves trajectory correctness and blending intensity, without a noticeable degradation in speaker similarity. Human evaluation prefers HybridEmo to CosyVoice 3 and EmoVoice-0.5B, with nearly balanced preferences against Qwen3-TTS.

cs.CL↗

arXiv2026

SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing

Instruction-guided speech editing requires a model to modify specified speech attributes while preserving non-target characteristics. Despite rapid progress in Speech Large Language Models (Speech LLMs), systematic evaluation of this capability remains challenging, as existing benchmarks are fragmented across isolated editing tasks. To bridge this gap, we introduce SpeechEditBench, a bilingual multi-attribute benchmark for instruction-guided speech editing. SpeechEditBench encompasses seven atomic editing tasks, as well as compositional editing tasks that integrate multiple operations within a single instruction. We propose an anchor-based evaluation protocol that separately assesses the edit success of target attributes and the preservation of non-target linguistic content, leading to three metrics: target success, preservation success, and joint success. Using this benchmark, we evaluate mainstream Speech LLMs and specialized speech editing systems. The results reveal three key findings: (1) no single model performs well across all editing dimensions; (2) closed-source Speech LLMs generally outperform open-source models; (3) compositional editing poses a significant challenge, with even the most advanced models struggling to achieve high joint success. SpeechEditBench provides a rigorous diagnostic framework to identify bottlenecks in Speech LLMs, thereby facilitating the development of next-generation models with more precise instruction-guided editing capabilities. Data and code are available at https://github.com/daxintan-cuhk/SpeechEditBench.

eess.AS↗