Speech
-
Personalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial Conversations
2026-10-02 08:52:00David Nadrchal, Monorama Swain, Florian Schmid, Gerhard Widmer, Paul PrimusAbstract
This work presents an automatic speech recognition (ASR) system personalized for a Czech speaker with a permanent tracheal stoma and severe dysarthria rendering their speech unintelligible to untrained listeners. We release a public dataset containing 33 annotated hours of the speaker's speech, collected using a novel "artificial conversation" protocol designed for high engagement and dialogue realism. We propose a multi-stage training pipeline based on Whisper Base: fine-tuning on standard Czech speech, acoustically simulated tracheostomic speech, and the speaker's data. We evaluate the system across three near real-time scenarios: scripted conversations, question answering, and spontaneous dialogue, achieving a 50\% relative reduction in Character Error Rate compared to Whisper Base baseline and surpassing the average recognition accuracy of their assistants in acoustic recognition of isolated utterances. We demonstrate that even for severely impeded speech, a helpful ASR is achievable, as evidenced by the quantitative results and the feedback from the speaker.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03017
PDF
-
DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs
2026-10-02 06:19:14Daewon Chae, Hyunwon Chung, Changwoo Lee, Hun-Seok KimAbstract
Large-scale foundation models achieve strong performance across diverse tasks, but their size makes inference costly, largely due to dense matrix multiplications. Prior work reduces this cost by replacing dense weight matrices with efficient structured forms such as low-rank factorizations. However, these methods approximate weights rather than the output activations that determine inference accuracy. Consequently, small weight-space errors can be amplified by input activations, producing large output errors. In this work, we propose DyRA, an input-adaptive method that improves structured matrix multiplication approximation by correcting residual output errors during inference. We show that matrix multiplication can be approximated more effectively by directly optimizing low-rank factors of the output. DyRA builds on this insight by dynamically approximating and correcting the output error introduced by structured weight approximations. This combines efficient structured computation with input-dependent correction, yielding a more faithful approximation of full matrix multiplication under the same computational budget. Across vision, speech, and language models, DyRA consistently improves the accuracy-efficiency trade-off over structured weight approximations alone. Notably, DyRA achieves a 1.5$\times$ end-to-end GPU speedup for DINOv3 while reducing accuracy degradation by more than 3$\times$ relative to weight-only baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02882
PDF
-
Correlation-Based Distillation Yields More Mergeable Speech-Music Encoders
Abstract
A single compact encoder for both speech and music removes the need to maintain a separate model per domain. A practical recipe distils a speech teacher and a music teacher into two small students, then merges them into one model. Two merging algorithms exist: interpolating the student weights from a shared initialisation, or permuting their channels into alignment before averaging. Prior work fixed the distillation loss in both, leaving open whether the loss itself affects how well the students merge. We show that it does. Holding architecture and evaluation fixed, we replace the DistilHuBERT loss \Lkd{} with a correlation-based loss \Lcl{}. Under weight interpolation, \Lcl{} students stay closer to their own better endpoint in $17$ of $18$ comparisons and lead on the speech tasks at every interpolated weight. Under activation permutation, they need fewer channels rearranged at three layers, their matched channels correlate more strongly, and they again lead on speech. The two merging algorithms share no mechanism, yet both improve under the same loss substitution. This suggests that the gain lies in the representation \Lcl{} produces rather than in either algorithm.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02836
PDF
-
What Actually Makes Correlation-Based SSL Distillation Noise-Robust? A Mechanistic Correction
2026-10-02 05:15:30Fabian Ritter-Gutierrez, Nancy F. Chen, Eng Siong ChngAbstract
Self-supervised learning (SSL) speech models are accurate but large. Knowledge distillation compresses them, but the student loses the teacher's noise robustness. Correlation-based distillation addresses this with two terms: cross-correlation aligning student and teacher's representations, and self-correlation decorrelating the student's features. Both the original method and De'HuBERT credited the self-correlation term without isolating it. We show the opposite. On LibriSpeech-100 distillation with held-out CHiME-3 noise at 10\,dB, an unbiased full-dimensional probe, a Pearson-variance decomposition, a same-noise causal control, and a per-dimension analysis identify the cross-correlation diagonal as the mechanism that encourages noise invariance, lowering noise-classification accuracy from 76.98\% to 55.02\%, whereas adding the self-correlation term back leaves it at 55.55\%. The self-correlation term instead reorganises the feature space and improves accuracy on the clean downstream tasks, but removes essentially no noise. Across nine speech and music tasks this yields a concrete design rule for distillation: weight the cross-correlation term for noise robustness, tune the self-correlation term for better downstream performance, and sample teacher and student noise independently.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02823
PDF
-
Automatic Evaluation of Mental Health Stigma in Online Communication
2026-10-02 04:02:56Naomi Baes, Jemima Kang, Nick Haslam, Chris Groot, Alsa Wu, Luc Raszewski, Yulia OtmakhovaAbstract
Mental health stigma has profoundly harmful impacts but its complexity makes it difficult to evaluate. Stigma may involve explicit derogation, but also subtler forms of blame, fear, paternalistic pity, social distancing, structural exclusion, and discrimination. We introduce a theory-grounded benchmark for automatic evaluation of mental health stigma in online communication, consisting of naturally occurring online news and social media text annotated with a fine-grained taxonomy of stigma across multiple mental health conditions. Our annotation framework comprises a binary stigma-detection task and a multi-level taxonomy covering (i) stigma mode, (ii) domain, and (iii) specific components of certain forms of stigma. We apply this framework to texts mentioning six mental health conditions and evaluate large language models alongside stigma-related classifiers for detecting sentiment, toxicity, and hate speech. Results show that mental health stigma is not well captured by models trained to detect these neighboring constructs, and that LLMs often overpredict stigma unless given explicit operational rules - mirroring the importance of decision rules in human annotation. We release the publicly available part of benchmark, annotations, prototypical exemplars of stigma and code at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02775
PDF
-
GAANet: Global-guided Asymmetric Attention Network for Audio-Visual Speech Separation
2026-10-02 03:29:56Zhiyuan Zhang, Jingyuan Xu, Yiming Tang, Liu Liu, Dan GuoAbstract
Multi-scale design is crucial for efficient audio-visual speech separation, yet effectively modeling multi-scale information for audio-visual feature fusion remains challenging. We argue that the limited capacity of existing approaches primarily arises from: 1) treating features from different modalities in the same manner, and 2) overlooking the role of global features. To address these issues, we propose a Global-guided Asymmetric Attention Network (GAANet). Our model introduces two core innovations: first, an asymmetric multi-scale fusion framework that allows audio and visual streams to extract and interact with features at their respective optimal temporal resolutions, removing the need for symmetric temporal downsampling; second, a global-guided attention mechanism that compresses each modality into a compact global token with a temporal dimension of one, which then provides high-level semantic cues to guide both intra- and inter-modal fusion across scales. Experiments on LRS2 and VoxCeleb2 demonstrate that GAANet achieves state-of-the-art performance, reaching 16.5 dB SI-SNRi on LRS2 and 14.0 dB on VoxCeleb2, while maintaining a lightweight computational profile with only 3.3M parameters and 19.8G MACs. These results highlight the strong potential of asymmetric temporal modeling and global guidance for efficient and robust multimodal fusion. The source code is publicly accessible at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.02752
PDF
-
Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript
2026-10-02 00:54:52Jie Jin, Ziyin Ma, Min Yin, Jinyu Chen, Haigang Song, Zhikun Pang, Xiaowen ZhangAbstract
Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which feeds ASR-encoder hidden states through a small connector into a frozen LLM and reads each question as a single-token distribution over its options. Nothing is decoded, and an 8-GPU node answers 80 decisions about eight utterances in about 0.1 s. With a last-layer connector, spoken QA stays close to reading the transcript (90% vs. 91%). DuplexJev also hears the speaker: gender and emotion accuracy both reach 90% (from 55% and 28%) with a cross-attention connector, whose spoken QA drops by only 1 point (83% to 82%). We train decisions with cross-entropy on the read-out answer token, instead of the usual transcript distillation, whose teacher never hears the voice, and keep distillation for content. Encoders and LLMs are interchangeable; we release weights, training recipe, a batched-inference pipeline for full-duplex serving and a bilingual spoken-QA set.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02638
PDF
-
Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation
Abstract
Simultaneous speech translation must emit useful target text before the source is complete while preserving every committed token. We adapt a full-utterance speech language model using prefix supervision derived from its own complete- and partial-waveform translations, requiring neither transcripts nor human translations. We compare single-turn forced-prefix and multi-turn append-only decoding, use a confidence threshold to control the inference-time quality--latency trade-off, and vary the density of training prefixes with a separate synthesis margin. On FLEURS and CoVoST2 in three language directions, prefix training improves quality--latency frontiers over the unadapted model, and confidence provides the broadest consistently competitive operating range. Multi-turn decoding is generally stronger at low latency; under multi-turn training, commit-calibration error falls by 63--68% overall and 68--80% at early prefixes, whereas single-turn training provides only modest overall calibration gains and no early-prefix improvement. A small synthesis margin sometimes extends the frontier to lower latency, particularly on shorter utterances, while a larger margin degrades translation quality and calibration. Prefix adaptation therefore improves simultaneous speech translation, especially under multi-turn append-only decoding, while synthesis density introduces a non-monotonic quality--latency trade-off.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02612
PDF
-
SocialVLA: A Social Perception Gateway for Human-Reaction-Based Failure Detection and Recovery in VLA Manipulation
2026-10-01 18:36:35Sofya Konstantinova, Miguel Altamirano Cabrera, Artem Lykov, Dzmitry TsetserukouAbstract
Vision-language-action (VLA) policies enable diverse robotic manipulation but can fail during execution without recognizing their own errors. Human observers provide complementary signals, as unexpected robot behavior can trigger rapid vocal, facial, or verbal reactions before failure is completed. We introduce SocialVLA, a local, policy-agnostic social perception gateway that converts spontaneous human reactions into runtime intervention signals for VLA manipulation. SocialVLA combines causal paralinguistic audio detection, visual reaction recognition, explicit stop phrases, and robot-relevance estimation. An asynchronous first-event fusion mechanism triggers a VLA hold from the earliest sufficiently confident signal, while a separate speech channel captures verbal corrections for participant-directed continuation, restart, or instruction revision. We evaluate SocialVLA on physical Unitree G1 manipulation using 15 participants, with 238 annotated intervention-worthy episodes and 1.038 h of non-intervention behavior. Frozen offline replay achieves 54.6% recall and 69.5% precision, while unfiltered audio-video fusion reaches 64.3% recall. Relevance estimation reduces false-stop episodes from 100 to 57 and increases precision from 60.5% to 69.8%. In prospective deployment on an unseen 16th participant, the frozen system achieves 59.5% recall and 91.7% precision. Median detector-to-fusion latency is 47.9 ms, VLA-gate-to-physical-hold latency is 336 ms, and reaction-onset-to-hold latency is 1.021 s. These results demonstrate a complete local pathway from spontaneous social reaction to physical VLA interruption and participant-directed recovery.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02360
PDF
-
Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
2026-10-01 17:49:40Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Sahal Shaji Mullappilly, Ivan Laptev, Hisham CholakkalAbstract
Extending a text embedding model to new modalities typically degrades text retrieval quality, and existing omni-modal embedders compensate with multi-billion parameters. We present Omni-Embed-Mini, a 0.9B-parameter model that maps text, speech, audio, images, video, and visually-rich documents into a single shared cosine space without updating any text-side parameter. Our key insight is that the teacher signal requires no separate embedding model: each media sample is paired with a dense cascaded caption, and the teacher target is simply the frozen backbone's own embedding of that caption. Because teacher and student share the same backbone weights, they inhabit byte-identical geometry, and lightweight projectors plus phased LoRA adapters on the modality encoders suffice for alignment. Training combines a Matryoshka SigLIP contrastive loss with an online hybrid hard-negative miner whose negatives sharpen as the encoder improves. The recipe carries over to a 2.3B variant by swapping in a native vision-language backbone. Omni-Embed-Mini-0.9B keeps its text weights bit-identical to the backbone, so training cannot regress text retrieval (49.57 nDCG@10 on MTEB-v2 BEIR-8), while extending it to five additional modalities, and is ~2.7x to 9.5x smaller than every open omni embedder we compare against. The 2.3B variant is competitive with the closed gemini-embedding-2, edging ahead of it on the overall-modality average. Models, code, data and evaluation harness are on our project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.02148
PDF
-
SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL
2026-10-01 16:43:27Hyeonmin Lee, Zheng Wei, Kyungmin Kwon, Jumin Seo, Jiwon Park, Hayoung OhAbstract
While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making immersive authoring a repetitive and physically fatiguing process. We present SPHERE, an adaptive VR generation framework that transforms isolated synthesis into continuous human-AI co-creation. SPHERE extracts persistent spatial preferences from natural multimodal interactions (speech and controller edits). To ensure geometric resilience against spatial distortions, it abstracts these raw edits into hierarchical constraints modeling both local functional and global topological contexts. Furthermore, a human-in-the-loop reinforcement learning mechanism dynamically updates retrieval policies based on the user's final edited scenes. A mixed-design user study ($N=42$) and an offline ablation demonstrate that SPHERE significantly reduces corrective edits and physical demand, preventing bias toward shallow object-level traits to yield geometrically resilient, profile-aligned layouts. Ultimately, SPHERE demonstrates how capturing demonstrated spatial logic enables controlled spatial adaptation, establishing a reliable, governed human-AI collaboration framework for immersive authoring. Project page and source code will be available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.02023
PDF
-
Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?
2026-10-01 15:13:19Serli Kopar, Alkis Koudounas, Roshan P. Rane, Sam Gijsen, Paula A. Perez-Toro, Kerstin RitterAbstract
Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representations directly from raw audio, exposing the model to recording factors. We ask whether such factors are merely encoded in SSL representations or can systematically alter predictions. Using ADReSSo and three large SSL backbones, we apply controlled noise and reverberation interventions to participant-speech-only, non-speech, and full-recording audio. We combine layer-wise linear decoding, input- and representation-space interventions, and geometric alignment analysis to distinguish acoustic decodability from influence on AD prediction. Our results show that controlled acoustic interventions alter AD predictions across all three SSL backbones. Noise, despite showing no significant diagnostic-group difference in the original data, produces the strongest intervention effects. Importantly, these effects are systematically structured relative to the classifier's decision direction, replicate on the held-out test set and reverse when the representation-space intervention direction is reversed. Together, these findings show that high predictive performance and the absence of a significant diagnostic-group difference in a measured acoustic factor are not sufficient for robustness. We argue that intervention-based robustness tests should become standard for trustworthy clinical speech models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01846
PDF
-
Exposing the Cost of Deep Learning Audio Development
2026-10-01 12:55:25Constance Douwes, Paul Magron, Romain SerizelAbstract
The environmental impact of deep learning has attracted increasing attention over the past decade. Existing studies mainly focus on the energy and carbon emissions of model training and inference, while the whole development phase is often overlooked. Yet, architecture prototyping and intensive experiments are conducted during this stage, which is highly energy-demanding. In this article, we propose a methodology to estimate these costs, based on activity logs from the Grid5000 shared computing platform used by the LORIA laboratory. As a case-study, we focus on audio projects developed in the Multispeech research team. We evaluate the overall energy cost of four projects, and we compare them to those of training the reported models. Our results show that the energy required for the development phase is 3 to 256 times greater than that required to train the best-performing model alone. These results advocate for a more systematic reporting of energy consumption across the entire life cycle of deep learning-based audio projects.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01619
PDF
-
Unified Shared Encoder in Spoof-Aware Speaker Verification with Hybrid Wavelet Prompt Tuning
2026-10-01 12:46:33Aref Farhadipour, Srikanth Madikeri, Teodora Vukovic, Volker Dellwo, Petr MotlicekAbstract
Spoofing-aware speaker verification (SASV) must confirm who is speaking and that the speech is genuine, but current systems gain one at the expense of the other. Modular cascades are accurate yet run two large self-supervised encoders, whereas end-to-end models are efficient but lose accuracy when a single embedding has to serve two conflicting objectives. We show that this trade-off between efficiency and specialization is avoidable. A single frozen W2V-BERT~2.0 backbone is adapted per task by deep hybrid Wavelet Prompt Tuning (WPT), so each branch obtains its own view of the shared encoder through dedicated prompts and a task head, and the scores are combined only at inference. Training only about 7M parameters, a small fraction of those a strong two-encoder cascade requires, the system surpasses it on SpoofCeleb evaluation with 0.03% CM-EER and 0.038 min a-DCF against 0.16% and 0.047. Because the backbone is shared and frozen, new branches attach without retraining the heads and prompts already in place. On ASVspoof5, with adversarial attacks and codec distortions, it reaches 0.092 min a-DCF and 3.60% CM-EER using only the provided data, indicating that the design holds under realistic in-the-wild threats.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08845
PDF
-
AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models
2026-10-01 12:28:03Yuxiang Wang, Kunyu Feng, Yuancheng Wang, Zihang Liu, Shengbo Cai, Qinke Ni, Wan Lin, Tao Feng, Yingda shen, Ming-Hao Hsu, Zhixian Zhao, Liqiang Zhang, Teddy Sun, Steve Yves, Zhizheng WuAbstract
Model intelligence and fast response jointly shape the quality of interaction with speech language models, yet remain difficult to achieve together. Explicit chain-of-thought (CoT) improves reasoning and audio understanding, but generating intermediate reasoning tokens delays responses. Describing fine-grained acoustic cues further lengthens CoT and increases latency. Latent reasoning can reduce this overhead, yet existing methods often trail CoT and remain limited by single-path supervision and reasoning budgets that do not adapt to problem difficulty. We introduce AURAL, which models a distribution over multiple plausible reasoning continuations in latent space and jointly predicts chunks of future states to reduce sequential forward passes and reasoning latency. To provide initial supervision for latent reasoning, we construct AuralReason-683K: 683K bilingual speech utterances (about 1,000 hours) with concise CoT for emotion recognition, empathetic dialogue, and general reasoning. AURAL-RL then explores beyond these traces, rewarding concise reasoning that yields high-quality answers and adapting reasoning effort to each problem. Across two backbones, AURAL-RL achieves performance comparable to CoT-RL, with larger gains over the respective supervised checkpoints on most metrics. Analysis further shows that harder questions elicit more latent reasoning steps. On Qwen2.5-Omni, it reduces time to the first answer token by 11.8x, from 1.22 to 0.10 s, versus 0.05 s for direct answering.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01560
PDF
-
UZH-CL at ArA-DF 2026: Prompt-Tuned Foundation Models and Track-Adaptive Score Fusion for Arabic Speech Deepfake Detection
2026-10-01 11:56:09Aref Farhadipour, Teodora Vukovic, Petr MotlicekAbstract
Detecting synthetic and voice-converted speech remains difficult for low-resource languages with dialectal diversity, where systems must generalize across regional dialects and unseen acoustic channels. We present the UZH-CL submission to the ArA-DF 2026 Shared Task on Arabic speech deepfake detection, covering Track~1 (dialect generalization) and Track~2 (acoustic robustness). We freeze a W2V-BERT-2.0 backbone and adapt it with \emph{Wavelet Prompt Tuning}, updating under 1% of parameters, and aggregate multi-layer representations with cross-layer attention and a general attentive-statistics pooling head rather than a specialized graph backend. Complementary detectors are obtained by varying adaptation strategy, training data, augmentation, and encoder family. We find that the two shift types require different fusion regimes: a broad multi-window ensemble for dialect generalization, and a compact, channel-matched, center-crop ensemble for acoustic robustness. Official evaluation yields 1.96% EER on Track~1 (6th place) and 1.04% EER on Track~2 (3rd place), corresponding to 87% and 96% relative reductions over the XLS-R+AASIST baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08844
PDF
-
Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization
2026-10-01 11:35:01Jeeyoung Yun, Seohwan Yun, Sungwoong KimAbstract
Neural speech codecs increasingly serve as tokenizers for speech language models (SLMs). Lowering the frame rate reduces the computational and memory costs of SLMs, but makes it difficult to preserve both linguistic information and acoustic detail. Existing approaches rely on rule-based compression: average pooling can discard linguistic information, whereas similarity-based merging uses a fixed threshold on adjacent-frame similarity and applies the resulting boundaries to the acoustic stream. We propose Q-SPT, a low-frame-rate dual-stream speech tokenizer with separate, context-aware, learnable query-based compressors specialized for semantic and acoustic representations. In particular, queries at a fixed rate independently attend to the semantic and acoustic streams as separate key-value sources, enabling stream-specific, context-aware aggregation through two separately learned compressors. In addition, an autoregressive text loss explicitly supervises the semantic compressor to preserve linguistic information. Experimental results show that Q-SPT achieves the best reconstruction among the evaluated codecs at the same frame rate. In downstream SLMs, it yields the best speech recognition accuracy and text-to-speech perceptual quality with competitive intelligibility.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01492
PDF
-
Generation Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
Abstract
Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused. A waveform-label pair does not preserve this knowledge. We propose a generation-provenance substrate in which a synthetic research object binds source specification, generated content, waveform, target, fact requirements, quality signals, review lineage, and immutable manifest identity. Producer and selection mechanism determine evidentiary meaning; storage location and variable name do not. We audit this substrate in a private Japanese care-handoff pipeline. A 113-asset review population contains 1.552 hours of synthetic speech across six scenario families; all items have linked audio, transcripts, candidate notes, and fact checklists, but human evidence is selective and source-specific. Two faithful-only manifests are scenario-seed-disjoint and immutably versioned, while exact upstream attribution remains blocked by floating generator aliases, missing per-clip TTS and code stamps, and an unversioned checking prompt. We argue that generation provenance is necessary but not sufficient for behavior attribution: it defines the candidate causal graph and audit units, whereas contributive attribution still requires frozen training runs and intervention or influence evidence. The paper contributes a compact provenance contract, an audit protocol, and a bounded case study for synthetic-data attribution; controlled research access may be offered, but we do not claim causal training-data attribution, clinical validity, or unrestricted public release.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01378
PDF
-
AudioJev: Direct Audio Decisions with Order-Calibrated Probabilities
2026-10-01 08:29:04Sihan Lv, Zhen Li, Zhiqi Cao, Jinshan Zhang, Ying Li, Meng Xi, Jianwei YinAbstract
Audio decisions often depend on evidence that a transcript does not preserve, while their probability estimates can depend on how answer options are ordered. AudioJev maps a waveform, question and supplied alternatives directly to a candidate distribution through one shared full-parameter model. We define order calibration as preserving an answer's probability under meaning-preserving option permutations. Random-derangement SKL training pairs each question with a reordered view in which every alternative changes position, supervises both answers, and aligns the two distributions before applying a symmetric KL penalty. Inference retains a single candidate-scoring forward, with no calibration head or order ensemble. Across three training seeds, AudioJev reaches 68.88%/55.33% mean accuracy on complete MMAU/MMAR and reduces random-order SKL by 43.8%/60.5% relative to the single-view removal ablation. The same model handles intent, environmental sound, note properties, speech activity and conversational transitions. Paired removal ablations and multi-order evaluation measure predictive accuracy and probability stability together, establishing a direct audio interface whose calibration objective acts on candidate meaning rather than presentation position. Inference code and model weights are available at this https URL and this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01293
PDF
-
ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning
2026-10-01 07:00:48Bingchen Pei, Lichong Chen, Bingxi Zhao, Ziang Wu, Sirui Wang, Min Zhang, Yanhao Chen, Qingxu Liu, Qiang Gao, Chang-Tien Lu, Bo GaoAbstract
Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction agent generates and validates the required media from the protected record. The remote solver returns a program whose protected operands are restored locally before execution. On 4,000 held-out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of unprotected remote accuracy, while a model-based audit flags source-content leakage in 7.95% of solver-bound requests. It outperforms all evaluated local baselines, preserving the benefit of remote reasoning while reducing source-content exposure under existing media interfaces.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01184
PDF
