arXiv_SD
-
EarLog: Opportunistic Ear Physiology Sensing toward Personalized Hearing Risk Awareness
Abstract
Many headphone users risk irreversible hearing damage during high-load listening, yet current protection still relies on sound-pressure limits. Clinical tests detect damage after it becomes measurable, leaving the risk-accumulating process unobserved. The acoustic reflex (AR), an involuntary response to high acoustic load, marks when the ear enters a protective state. AR traces are weak, and existing measurements require dedicated probes and controlled conditions that are difficult to maintain during everyday audio. We present EarLog, which turns playback, the dominant interference, into an opportunistic probe. EarLog introduces content-conditioned residual sensing to suppress variations caused by nonstationary content, individual ear acoustics, and device response. It identifies weak AR through loudness-dependent changes and localized spectral irregularities in the residual. A resonance-constrained sparse finite impulse response (FIR) model captures the short-window response. Dual-microphone observations, mild-distortion recovery, and cross-session reference updates keep detection usable under low signal-to-noise ratio (SNR), fit changes, and environmental drift. EarLog runs in real time on an embedded controller using a low-cost dual-microphone add-on. We evaluate it with 81 participants, 16 headphone models, and more than 400 hours of recordings. EarLog achieves 99.0% sensitivity and 98.7% specificity on a clinically referenced benchmark. EarLog records listener-specific AR events during everyday listening, providing data for future longitudinal studies of hearing risk.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12501
PDF
-
Improving Predicted MOS Scores, Not Perceived Quality: Multi-Predictor Test-Time Optimization of Enhanced Speech
2026-09-30 05:33:40Tsubasa Ochiai, Marc Delcroix, Nahomi Kusunoki, Rintaro Ikeshita, Naohiro Tawara, Naoyuki Kamo, Tetsuji Ogawa, Shoko ArakiAbstract
Non-intrusive MOS predictors are widely used instead of subjective listening tests to evaluate and rank speech enhancement (SE) systems. If they accurately reflect perceived quality, raising their scores should lead to higher-quality speech. We present the first comprehensive analysis of test-time optimization for the SE task, which directly modifies the enhanced signal to raise the average of multiple MOS predictor scores. On seven systems from the URGENT 2026 challenge, we find that 1)~all the optimized predicted scores increase while reference-based metrics remain nearly unchanged, 2)~a non-optimized predicted score does not increase, and 3)~a MUSHRA listening test shows no improvement in perceived quality. These findings reveal a risk that such optimization can distort evaluations, e.g., biasing comparisons of SE systems regardless of their perceived quality. We believe these findings can inform future evaluation practices: they suggest that predictors used for optimization should not be used for evaluation, and that challenges should keep the predictors used for ranking undisclosed.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39028
PDF
-
Intonation Perception in Real and Synthetic Speech across Varying Familiarity Levels: A Pilot Study of Equivalence Assessment
2026-09-30 02:32:37Hanrui Zhou, Gaoyuan Zhang, Yixiang Chen, Yujie Xing, Feng Xu, Xurong Xie, Hui ChenAbstract
Language training relies on a corpus constructed by a large number linguistic materials. AI-powered voice clones provide a way to construct the corpus with relatively low cost. Singing voice conversion (SVC) model is used to generate synthetic voices. This study compares participants' performances on natural and synthetic speech in two experiments, similarity perception and intonation recognition. In the accuracy of similarity perception task, a significant interaction between speech type and intonation is found, suggesting that question may serve as a cue for speaker identification but may be influenced by synthetic features. In the accuracy of intonation recognition task, a significant interaction between speech type and familiarity is observed, indicating that speech type affects how much familiarity contributes to voice processing.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08839
PDF
-
A barrier or a booster? Familiarity effects on Mandarin emotion prosody recognition using AI-powered voice cloning
2026-09-30 02:26:48Feng Xu, Gaoyuan Zhang, Shanshan Xue, Yixiang Chen, Hanrui Zhou, Xurong Xie, Hui ChenAbstract
Emotion prosody perception requires simultaneous processing of acoustic cues and speaker identity. While listeners effortlessly decode natural speech, AI synthetic voices introduce cognitive complexities due to subtle acoustic atypicalities. It remains unclear how these synthetic features interact with a listener's prior social knowledge and memory of a familiar speaker. This study investigated how speech sources (human vs. AI) and speaker familiarity affect emotion recognition accuracy and cognitive load. A within-subject task with Mandarin-speaking adults evaluated behavioral (accuracy, reaction time) and physiological data (heart rate variability). Results showed that human voices yielded significantly higher accuracy and faster processing times than AI voices, while HRV did not significantly differentiate between conditions. These findings show that decoding synthetic speech is gated by top-down social cognition, highlighting limitations in current AI synthesis technologies.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38794
PDF
-
Acoustic Biomarkers for Alzheimer's Disease Detection from Spontaneous Speech
2026-09-30 02:15:12Anh L Tran, Arjee Javellana Restar, Bereket KindoAbstract
Alzheimer's disease (AD) remains a major public health challenge, and early identification is crucial for timely intervention and care planning. Recent work has shown that speech-based digital biomarkers can capture subtle changes in vocal production, prosody, and timing that often precede or accompany cognitive decline. In this study, we investigate whether acoustic features extracted from spontaneous speech can reliably distinguish individuals with AD from healthy controls. Using a structured speech dataset derived from the Cookie Theft picture-description task, we extract clinically informative low-level descriptors spanning prosodic, spectral, and temporal domains, and evaluate a range of machine learning classifiers. Our results indicate that acoustic biomarkers carry strong discriminative value, with the best-performing models achieving clinically meaningful separation between diagnostic groups. These findings support the use of non-invasive, low-cost audio-based screening tools and motivate further work on multimodal and longitudinal assessment frameworks for dementia risk detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12500
PDF
-
Multi-Rate Bandwidth Extension by Token Completion in Neural Audio Codecs
2026-09-29 20:25:54Beno\^it Ginies, Olivier Fercoq, Ga\"el RichardAbstract
Bandwidth extension, the task of reconstructing the high-frequency components of an audio signal from its low-passed counterpart, is a long-standing problem in audio processing. In this work, we extend recent advances in neural architectures by framing bandwidth extension as an audio token prediction problem. Specifically, we train a transformer-based language model on the discrete representations produced by a disentangled neural audio codec, where the disentanglement is guided by a Harmonic-Percussive decomposition of the input signals, highlighting spectral structures particularly relevant for bandwidth extension. Our approach introduces a novel codec design that explicitly accounts for the downstream token prediction task, enabling a more effective coupling between codec structure and transformer modeling. This joint design yields high-quality reconstructions of the original signal, as measured by both objective metrics and subjective evaluations. These results highlight the importance of aligning codec disentanglement and representation learning with the generative modeling stage, and demonstrate the potential of global, representation-aware design for advancing bandwidth extension.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38502
PDF
-
Voices as Handles: Reasoning about Speaker Identity with Frozen Text LLMs
2026-09-29 20:25:40Runqiu Xu, Zhisheng Zheng, David HarwathAbstract
Multi-user voice agents must track who said what across dialogue sessions. Text LLMs are attractive backbones for such agents, but transcripts alone do not expose acoustic speaker identity, leaving the model without a persistent reference for linking information to speakers across sessions. We address this gap by introducing Speaker Handles, soft-token representations that expose acoustic speaker identity to a frozen text LLM for cross-session speaker-dependent reasoning. A three-stage curriculum trains a lightweight projector, with fewer than 0.1% of the backbone's parameters, to map speaker embeddings into these handles. Establishing whether the resulting handles truly support cross-session speaker-dependent reasoning is challenging with existing benchmarks because textual cues can partially reveal fact ownership. We therefore present SpeakerBind, a controlled shared-agent benchmark in which overlapping facts across users require correct cross-session speaker attribution. Speaker Handles achieve 97.40-98.36% accuracy on VoxCeleb1 and 70.40% on SpeakerBind, close to the 71.88% topline. These results show that the proposed Speaker Handles provide an efficient way to integrate acoustic speaker identity into frozen text LLMs for speaker-content reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38501
PDF
-
Role-guided Speaker Deletion Verification in Clinical Psychiatry Speech Recordings with Audio Language Models
2026-09-29 20:20:24Joseph T Colonel, Daniel Katzman, Kelsey Kirker, Adam N Davidson, Shalaila S Haas, Cheryl Corcoran, Ren\'{e} S Kahn, Guillermo Checci, Baihan LinAbstract
Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Yet evolving consent and protocol requirements can oblige investigators to remove a designated speaker from multi-speaker recordings and to verify said removal at a scale infeasible for manual review of entire corpora. We study this verification problem for role-driven dyadic clinical dialogue in psychiatry and investigate it with two parallel, symmetric pipelines: confirming that clinician speech has been removed from psychiatric interview recordings, and confirming that patient speech has been removed from the same recordings. Each pipeline redacts the raw audio for its target role and then scans the surviving output with audio-language and large-language models to identify missed deletions. We evaluate this approach on a corpus of 48 dyadic recordings drawn from psychiatry settings, testing four open-weight models in an inference-only setting: Gemma-4-12B, Gemma-4-31B, Nemotron-3-Nano, and Nemotron-3-Nano-Omni. A disjunctive OR ensemble over fourteen model-view configurations had a combined F1 of 0.478 (precision 0.330, recall 0.870), an improvement over individual model estimates driven by recall gains that point to substantial complementarity across models and context views.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38491
PDF
-
2-Dimensional spectral gating for denoising bioacoustics recordings
2026-09-29 16:06:48Julien Boussard, M\'elisande Teng, Sulagna Saha, Mario Gallego-AbenzaAbstract
Isolating vocalizations from noise in bioacoustics recordings is a prerequisite to many ecological analyses, including species identification, animal communication understanding, and individual or population-level variability studies. However, when recordings are acquired in open environments, vocalizations, noise, or signal-to-noise ratio can vary widely across individuals, species, environment, and recording conditions, making it hard to develop robust and generalizable methods for ecological analyses. To account for these challenges, noise reduction techniques are used to remove noise before downstream analyses. Popular methods such as Noisereduce rely on spectral gating, which estimates a noise threshold for each frequency channel. We propose a further improvement to Noisereduce, leveraging the fact that most animal sounds have structure across multiple frequencies. We apply our method on bird and marine mammals recordings and show that our extension of Noisereduce leads to improved denoising in both above and under water acoustic recordings, without impacting speed of preprocessing.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37910
PDF
-
Do Music Generative Models Understand Musical Qualities? Automatic Music Evaluation with Model-Intrinsic Signals
Abstract
Current music generative models can produce high-quality music, but does this ability imply that they ``understand'' the musical qualities of their outputs, and is that understanding aligned with human evaluation? Previous attempts to use the likelihood of a generative model to evaluate music, an approach commonly used in text, have proven unsuccessful, leading researchers to rely on standalone supervised music evaluation models. In this paper, we answer this question affirmatively: we show that a model's intrinsic signals---derived from its hidden representations and predictions---are strongly correlated with human ratings. In particular, we study MusicGen and consider three types of features: (1) prediction loss, (2) prediction entropy, and (3) concepts extracted from the model using a sparse autoencoder (SAE). Using these features, we train a lightweight prediction model to estimate subjective ratings. We evaluate these features both individually and in combination. We hypothesize that these signals parallel the listening process: the temporal and frequency-domain structure of loss and entropy reflects listeners' expectation and surprise, while gradient directions in SAE latent space predict perceived quality. Experiments on five human-evaluation benchmarks spanning continuous ratings and pairwise preferences confirm this hypothesis, with SAE latents carrying most of the predictive signal.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37710
PDF
-
Rate-Agnostic Bioacoustics: Heterogeneous Multi-Taxa Classification with Continuous Filterbanks and Fourier Neural Operators
2026-09-29 13:21:40Stefano Ciapponi, Francesco Ardan Dal R{\i}, Nicola Conci, Elisabetta FarellaAbstract
Conventional bioacoustic classification models rely on fixed-rate spectral representations, requiring recordings acquired at heterogeneous sampling rates to be resampled before analysis. We propose a Sampling-Frequency-Independent (SFI) frontend that processes each recording directly at its native sampling rate, coupled with a Fourier Neural Operator (FNO) backbone featuring progressive temporal-scale fusion. This framework avoids fixed-rate resampling and high-frequency information loss while producing fixed-size representations across sampling rates. Mild training-time sampling-rate (\textit{sr}) augmentation further improves robustness to unseen rate variations. Evaluated on a multi-taxa corpus comprising 84 classes and 60 sampling rates, the proposed SFI-FNO configuration outperforms fixed-rate and corpus-maximum-rate baselines, achieving .906 accuracy, .921 balanced accuracy, and a Macro-F1 score of .899.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37540
PDF
-
Bad: Taming the Bioacoustic Data Deluge with a Bat Acticity Detector
2026-09-29 13:10:05Stefano Ciapponi, Santiago Martinez Balvanera, Andrea Cesaretti, Elisabetta Farella, Kate E. JonesAbstract
Passive Acoustic Monitoring of bats generates massive ultrasonic datasets (>27 GB/night per node), straining edge storage and battery life. Legacy triggers fail against acoustic confusers, while deep models exceed microcontroller limits. We present a hardware-aware Bat Activity Detector (BAD) specifically designed to discriminate bat calls from hard biological and environmental confusers across variable sampling rates (192-384 kHz). Tailored for the Silicon Labs EFM32PG26 (MVP) in 8-bit integer precision, our model achieves 100 percent hardware offload across all 14 layers (17.2 KB Flash, 73.1 KB RAM). End-to-end preprocessing (74.00 ms for 76 frames) and inference (30.00 ms) of 100 ms clips at 192 kHz require 104.00 ms per clip. On spatially out-of-domain recordings under a realistic low-prevalence regime (r_pos = 0.05), BAD achieves an AUC-ROC of 0.9748 and suppresses 99.4% of non-target noise frames while retaining 65.3% of bat calls - delivering a >33x precision gain over classical Goertzel baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37518
PDF
-
JoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint Representation
2026-09-29 10:12:21Yafeng Chen (Intern), Boya Dong (Intern), Yankun Huang (Intern), Hao Li (Intern), Jingdong Li (Intern), Xiangyu Liang (Intern), Hao Ni (Intern), Wenchao Wang (Intern), Yuxuan Wang (Intern), Zhangyu Xiao (Intern), Wei Deng (Intern), Nan Duan (Intern), Yu Gu (Intern), Wenhao Guan (Intern), Weisheng Han (Intern), Yabin Li (Intern), Yuan Liu (Intern), Jiaxin Ye (Intern), Fan Yu, Lin ZhuAbstract
We present JoyAI-Voice~2.0, an end-to-end anthropomorphic speech generation model built upon a fully continuous, dual-encoder architecture. Raw speech is encoded into continuous latents and partitioned into patches. Each patch is decomposed by a semantic-acoustic dual encoder into a semantically purified representation and an acoustic representation, which are fused and jointly fed to a causal autoregressive Transformer for planning. The Transformer predicts the conditioning for the next patch, and a local diffusion Transformer renders its full latents for 48\,kHz synthesis. The model is trained with a joint flow-matching and stop-prediction objective, followed by supervised fine-tuning and reinforcement learning with DiffusionNFT to improve model performance. It achieves the lowest average word error rate of 2.51\% on Seed-TTS, a 14.9\% relative reduction over the strongest baseline, and state-of-the-art attribute fidelity on InstructTTSEval in both Chinese and English, leading on 5 of 10 perceptual dimensions with the highest overall score of 0.893 on MDVD-Eval.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08834
PDF
-
Prediction-Layer Branch Calibration for Multimodal Sentiment Analysis
2026-09-29 09:20:55Yulin Sun, Kele Xu, Yong DouAbstract
Multimodal sentiment analysis integrates textual, acoustic and visual cues, yet current language-model-based fusion methods typically leave prediction-layer branch allocation implicit. We introduce Branch-Calibrated Multimodal Language Fusion (BC-MLF), which explicitly models prediction-layer branch allocation through a Branch-Calibrated Task Head (BCHead), complemented by Fusion Token Contrastive Learning (FTCL) for sentiment-aware fusion-token regularization. FTCL organizes mean-pooled fusion-token representations according to continuous sentiment affinity, while BCHead combines fusion, text and audiovisual predictions through a lightweight sample-adaptive constrained mixture. Without modifying the fusion backbone, BC-MLF consistently improves the reproduced DeepMLF baseline and achieves the strongest results among the compared methods on CMU-MOSEI and CH-SIMS across classification and regression metrics. The controlled ablations show that sample-adaptive prediction-layer branch allocation consistently outperforms static branch aggregation. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37100
PDF
-
RAWD-TTS: Ratio-Free Reward Alignment for Discrete-Diffusion Voice Cloning
2026-09-29 08:42:33Maxim Maslov, Kirill Borodin, Vasilii Kudryavtsev, Nikita Vasiliev, Grach MkrtchianAbstract
Zero-shot text-to-speech synthesizes new utterances in a speaker's voice from a short reference recording. Voice cloning requires accurate content and preserved speaker identity, but supervised acoustic-token prediction does not directly optimize these waveform-level properties. Reward-based post-training addresses this mismatch, but in discrete diffusion, token choices and reveal positions jointly define the sampling trajectory, complicating alignment. We introduce RAWD-TTS (Ratio-free Advantage-Weighted Denoising), which scores decoded samples with recognition and speaker rewards and uses group-relative advantages to weight masked-token reconstruction of those samples, without reverse-trajectory likelihoods or target audio. On 500 Russian CV3-Eval voice-cloning prompts, joint alignment reduces word error rate from 3.18% to 2.42% at the reward-selected checkpoint (24.0% relative) and to 2.58% at the final checkpoint (19.0%), while WavLM speaker cosine rises from 0.733 to 0.748 and 0.755. Controlled experiments characterize recognition-identity trade-offs and the effects of corruption count, group composition, and weighting.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37028
PDF
-
ReDimNet2+: Multi-Corpus Data Scaling for Robust Speaker Verification
2026-09-29 08:34:01Kirill Borodin, Vasilii Kudryavtsev, Maxim Maslov, Grach MkrtchianAbstract
Automatic speaker verification must remain reliable across devices, rooms, and compression pipelines. We present ReDimNet2+, which scales training of the compact ReDimNet2 backbone across seven public corpora (63,934 speakers, about 8,675 hours). Analysis of a VoxBlink2 subset reveals a shift in predicted spectral coloration, motivating codec and waveform augmentation alongside this multi-corpus training, large-margin fine-tuning (LMFT), and graph-based retrieval reranking. With random 4-second evaluation windows for all models, ReDimNet2+ LMFT reduces pooled VoxCeleb1 EER from 2.42% to 0.82% and a 26-condition robustness stress-test EER from 7.21% to 1.99%. Under this shared local protocol, it reaches 0.35% EER on VoxCeleb1-O versus 0.787% for the best evaluated WeSpeaker checkpoint. On a VoxBlink2 retrieval subset, reranking improves the final model's Pr@k from 0.7413 to 0.7687.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37014
PDF
-
RVQ Position Aware Speculative Decoding for On Device Text to Speech
2026-09-29 08:31:49Berkin Durmus, Eduardo Pacheco, Zach Nagengast, Atila OrhonAbstract
Autoregressive decoding (AR) with Transformer models is memory bandwidth bound at single stream inference, the typical deployment regime for on device text to speech (TTS). Real time streaming with Qwen3-TTS requires more than 200 sequential model calls per second, dominated by the inner loop MultiCodeDecoder that emits the 15 residual vector quantization (RVQ) codes per 80 ms audio frame. We propose RVQ position aware speculative decoding for the MultiCodeDecoder, attaining 2.47 accepted tokens per model call at $5\times10^{-4}$ percent added parameters and 10 to 20 percent per round speculation/verification overhead, reducing real time synthesis from 200 to 88 sequential model calls per second. The scheme is distributionally lossless under the deployed top-k sampling, and WER parity with the original system is consistent with this guarantee. We deliver 2 to 2.2x speedup for RVQ token generation with Qwen3-TTS 0.6B on recent iPhone and Apple Silicon Mac devices.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37007
PDF
-
Louder, Longer, Livelier: Acoustic Shortcuts and Underspecified Rationales in Speech LLM Judges
2026-09-29 08:15:29Mingyue Huo, Shivam Mehta, Bhavin Jawade, Yinghong Lan, Haoqi LiAbstract
LLM-as-a-judge is widely used for evaluating text, but extending this paradigm to speech requires models to interpret acoustic as well as linguistic evidence. This introduces a modality-specific risk: a speech judge may treat a perceptually salient cue as evidence of quality even when that cue is irrelevant to the target criterion or receives more weight than human listeners give it. We call this behavior an acoustic shortcut. To study it, we audit six speech LLM judges using controlled manipulations of intensity, content richness, and emotional delivery. We evaluate both pointwise scoring and pairwise comparison, using human preference calibration to interpret the results. The judges consistently reward louder audio, prefer content-rich speech more strongly than human listeners do, and map emotional delivery into quality preferences. These effects are most visible in pairwise comparison, while pointwise scores often obscure them. More concerningly, the accompanying rationales rarely identify the acoustic cue that changes a judgment and instead repeatedly rely on a limited vocabulary, leaving them acoustically underspecified. Together, these findings show that reliable speech judges must both resist acoustic shortcuts and ground their rationales in the acoustic evidence behind their decisions. To support reproducibility and future audits, we also release SpeechJudgeAudit, the controlled stimuli and evaluation tools used in this study.
Abstract (translated)
URL
https://arxiv.org/abs/2609.36979
PDF
-
Interpreting and Evaluating Dynamic-Rate Speech Codec Boundaries
2026-09-29 07:55:57Han Wang, Jiaqi Li, Yingda Shen, Yuxiang Wang, Zhizheng WuAbstract
Dynamic-frame-rate neural speech codecs replace a uniform frame grid with variable-duration tokens, making boundary placement part of the representation itself. Yet it is unclear what these boundaries encode and whether interpretable boundaries are also useful for neural speech reconstruction. This work combines boundary interpretation and controlled reconstruction analysis by comparing predicted boundaries with linguistic and acoustic references. We find that boundary meaning depends on the underlying speech representation. For the ASR-oriented SenseVoice and Whisper encoders, shallow layers emphasize phonetic, voicing, and acoustic transitions, whereas deeper layers shift toward syllable and subword structure. In a comparison of six dynamic-frame-rate algorithms and a uniform (fixed-frame-rate) baseline, higher-level linguistic alignment is associated with lower pooling distortion and better reconstruction from semantic tokens. Frame-rate-matched boundary tests make the distinction concrete: a syllable-derived partition improves over both Uniform and Similarity, while a phoneme-derived partition does not improve over Uniform. We infer that for semantically rich speech representations, useful codec boundaries are best understood as allocation decisions organized around the syllable scale.
Abstract (translated)
URL
https://arxiv.org/abs/2609.36951
PDF
-
When Capabilities Fail to Compose: Diagnosing the Compositionality Gap in Large Audio-Language Models
2026-09-29 07:40:51Chien-Feng Liu, Chih-Kai Yang, Bo-Han Feng, Yu-Hsuan Li Liang, Hung-yi Lee, Cheng-Fu ChouAbstract
Large audio-language models (LALMs) perform strongly on individual audio tasks, but whether these capabilities can be reliably composed remains underexplored. We conduct a controlled diagnostic study of capability composition in LALMs, requiring models to integrate audio-attribute recognition, cue-conditioned segment selection, and downstream ASR or question answering. We construct two-utterance inputs with distinct acoustic cues to evaluate composition across environmental sound, gender, and emotion cues, with ASR, Math QA, and Factual QA as downstream tasks. Across four open-source LALMs, compositional QA accuracy decreases in 39 of 40 model-task-cue settings, by an average of 26.7 percentage points. ASR exhibits a similarly consistent degradation, with WER increasing in 39 of 40 settings by an average of 28.5 percentage points, while the magnitude of degradation varies across models, cue types, and cue salience. We further probe these failures through output format, positional preference, and chain-of-thought (CoT) analyses. Our study reveals a systematic gap between possessing individual audio capabilities and reliably composing them.
Abstract (translated)
URL
https://arxiv.org/abs/2609.36921
PDF
