Recognition
-
Vision: 'What Don't I Know About User's Preferences?' How Uncertainty Estimation Improves Proactive Assistant Alignment
2026-10-11 22:13:37Zhiyu An, Ziyi Xuan, Yu Yang, Wan DuAbstract
Proactive Smart Assistants (PSAs) increasingly use general knowledge, learned patterns from group-level data, patterns from individual user's data, and recent sensor observations to anticipate which action a user may prefer. Existing systems typically select actions from predicted user preference likelihoods, but these likelihoods alone do not reveal how reliable the prediction is, which evidence supports it, or why ambiguity remains. In this vision paper, we argue that uncertainty estimation can provide this missing information and substantially change appropriate downstream behavior. Using the example of a home assistant, we introduce the questions that uncertainty estimation aims to answer, i.e. how sure is the assistant about the predicted preference likelihood, whether the confidence come from group-level assumptions or individual's data, and whether likelihood ambiguity reflect the user's intrinsic preference variability or insufficient data for the particular situation. We further introduce uncertainty estimation applications in neighboring domains, such as human trajectory prediction, personalized activity recognition, information-collection, and model-based control. Finally, we draw on insights from neighboring domains to envision how future uncertainty-aware proactive assistants may address key challenges in proactive interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15948
PDF
-
Learning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition
2026-10-11 20:13:12Yunxiang Luo, Constantino \'Alvarez Casado, Xiaoting Wu, Nhi Nguyen, Le Nguyen, Manuel Lage Ca\~nellas, Miguel Bordallo L\'opezAbstract
Predictive video representations do not by themselves specify how a multimodal system should handle missing sensors. We transfer frozen V-JEPA2 features to a set of heterogeneous sensors comprised by RGB video, depth video, and radar time series. A shared fusion model uses modality queries, fixed sensor slots, and explicit availability to classify breathing activity and pose from all seven non-empty sensor subsets. The contribution is a controlled evaluation of subset supervision, pooling capacity, and representation transfer on 39 OMuSense-23 subjects with five subject-group folds and three seeds. With matched downstream parameter counts, the final model reaches recording-level activity macro-F1 of $75.23%\pm0.60$ averaged across seven subsets. Supervising all subsets in each batch improves the matched query-pooling control by 1.923 percentage points (conditional 95% subject-bootstrap interval [0.647, 3.209]), while query pooling shows no clear advantage over matched mean pooling under balanced supervision. Radar probes support transfer beyond pooled wavelet pixels, 64-token inference approximately preserves mean activity performance, and the tested Consensus-JEPA loss adds no measured benefit against its exact control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15891
PDF
-
Synthesizing Ultrasonic Echo Profiles from Text for Open-Vocabulary Silent Speech Recognition
2026-10-11 14:49:19Jiacheng Liu, Ruidong Zhang, Fran\c{c}ois Guimbreti\`ere, Cheng ZhangAbstract
Eyewear that senses articulation with inaudible ultrasound can now recognize silent speech over an open vocabulary, but its accuracy is limited by the cost of training data. We present SoniGAN, which synthesizes the ultrasonic echo profiles of silent articulation from text and uses them as synthetic supervision. A voice-cloned text-to-speech (TTS) model reads a text corpus, and a two-stage generator synthesizes echo profiles from representations of the spoken content of that audio. Pretraining a recognizer on 104 hours of the synthesized data improves the word error rate (WER) of a public open-vocabulary benchmark by 2.3 points. Adding the sessions the corpus discards for a faulty microphone brings the system to 22.2% without any language model. Lexicon-constrained decoding, LLM rescoring, and ensembling further bring it to 14.9%, the first minimally obtrusive silent speech interface to fall inside the error range in which users report no loss of willingness to use silent speech input.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15671
PDF
-
Learning from Real Stuttering: Synthetic Mandarin Stuttering Speech for Data Augmentation in Speech Recognition
2026-10-11 07:18:30Yao Lu, Jiaming Zhou, Zhongyuan Fu, Yong QinAbstract
Mandarin stuttered speech remains under-resourced, limiting the development of robust speech processing systems. We present a Mandarin stuttering speech synthesis and data augmentation framework that adapts both autoregressive and non-autoregressive TTS models using naturally stuttered speech. Specifically, we adapt CosyVoice2 and MaskGCT to support controllable generation of specific stuttering events while also modeling broader utterance-level characteristics of stuttered speech. Using the adapted models, we construct synthetic data resources for downstream augmentation. Evaluations show that the generated speech closely approaches real stuttered speech. Extensive ASR experiments demonstrate consistent augmentation gains and further observe a domain-gap--diversity trade-off between synthetic and real data. These results demonstrate the value of learning synthetic stuttering data directly from real dysfluency for robust Mandarin speech processing.
Abstract (translated)
URL
https://arxiv.org/abs/2606.21457
PDF
-
CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition
2026-10-11 03:06:40Xiangqing Lu, Tao Zhu, Mingxing Nie, Liming ChenAbstract
Large language models (LLMs) offer a new approach to wearable-sensor-based human activity recognition. Retrieval-augmented generation (RAG) further introduces similar motion examples and discriminative sensor knowledge, enabling decisions grounded in observations relevant to the current query. More evidence, however, does not necessarily mean better-organized evidence. When online prompts and LLM agents primarily orchestrate inference, decisions about which activities to compare and when to invoke discriminative knowledge remain concentrated at inference time. As the activity vocabulary grows, the model must repeatedly process more candidates and associated knowledge, whereas pruning candidates too early risks excluding the true activity. We propose confusion-hierarchy evidence-aware reasoning (CHEAR), which moves part of this knowledge organization offline. CHEAR constructs and validates an activity hierarchy from recurrent cross-subject retrieval errors and builds corresponding activity-pair knowledge. At inference time, the hierarchy orders candidate comparisons; the LLM retains candidates progressively, and local discriminative knowledge is accessed only for the remaining activities. Across eight datasets, CHEAR achieves 86.79\% mean cross-subject accuracy, a 75.91\% candidate reduction rate, and 96.44\% true-activity retention. Per-sample token use is 85.15\% lower on average than in a variant without the hierarchical structure. Mean accuracy across eight cross-dataset transfer directions is 88.81\%. These results show that organizing candidates and discriminative knowledge around observed activity confusions reduces online LLM input while maintaining recognition performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15298
PDF
-
OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition
2026-10-11 02:57:12Xiangqing Lu, Tao Zhu, Liang Yu, Shuangjian Li, Lulu Ban, Furong Duan, Mingxing Nie, Liming Chen, Yaping WanAbstract
LLMs increasingly support sensor-based human activity recognition (HAR) by linking motion signals with activity semantics and physical knowledge. Retrieval-augmented generation (RAG) grounds decisions in sensor examples and domain features, enabling training-free target-user inference with less dependence on raw numerical arrays. However, existing LLM/RAG-based HAR typically searches single-level activity spaces using static population knowledge. Consequently, they compare many unrelated candidates using the same static population evidence and overlook personalized motion patterns. We propose OntoAR-HAR, an ontology-guided agentic RAG framework combining static population and personalized knowledge. Its tree-structured activity ontology decomposes classification into local decisions among semantically related activities. The static store supplies node-constrained examples, while offline-discovered executable signal features provide numerical evidence for local distinctions. During inference, the personalized store collects selected user observations, which the LLM integrates with static knowledge and signal features while traversing the ontology to an activity label. Cross-subject and heterogeneous-sensing experiments show complementary gains from hierarchical retrieval and personalized memory across multiple LLM backbones, achieving state-of-the-art performance. By explicitly modeling hierarchical relations across activity granularities, OntoAR-HAR also addresses the long-overlooked semantic inclusion problem and avoids treating related labels as independent categories.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15292
PDF
-
GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?
2026-10-10 19:15:11Zonghuan Li, Hayley Hung, Chirag RamanAbstract
Human social perception is incremental: we infer intent before an utterance is complete, revise our interpretation as new cues arrive, and attend to specific facial, gestural, or prosodic signals that shape social meaning. Current multimodal LLM benchmarks largely evaluate final-answer understanding over complete episodes, rewarding post-hoc recognition of social meaning rather than the unfolding perception required for real-time interaction. Drawing on interactionally embedded Gestalt principles of multimodal human communication, we introduce GesBench: a human-grounded benchmark for cue-level social perception in multimodal LLMs. GesBench uses cumulative sub-utterance clips to measure when models form stable interpretations of speaker intention and social affordance, and human gaze-guided corruption to evaluate whether regions attended by humans are functionally important for model judgments. Built from more than 6000 utterance-level clips from scripted and unscripted conversational datasets, GesBench includes human annotations of unfolding judgments and gaze on a representative subset. Across open and closed multimodal models, we find a clear human-model gap: humans form predictive understandings early and revise more often, while models often hedge or repeat across different clips. GesBench shifts social evaluation from whether models eventually recognize meaning to when and where that meaning is formed. Our codes are publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15129
PDF
-
RIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition
2026-10-10 19:01:49Reem Abdel-Salam, Rana Mostafa, Ahmed H. Abdel-GawadAbstract
Traffic sign recognition plays a crucial role in the development of autonomous cars to reduce the accident rate and promote road safety. It has been a necessity to address traffic signs that are affected significantly by the environment as well as poor real-time performance for deep-learning state-of-the-art algorithms. In this paper, we introduce Real-Time Image Enhanced CNN ({\our}) for Traffic Sign Recognition. {\our} is a real-time, novel approach that tackles multiple, diverse traffic sign datasets, and out-performs the state-of-the-art architectures in terms of recognition rate and execution time. Experiments are conducted using the German Traffic Sign Benchmark (GTSRB), the Belgium Traffic Sign Classification (BTSC), and the Croatian Traffic Sign (rMASTIF) benchmark. Experimental results show that our approach has achieved the highest recognition rate for all Benchmarks, achieving a recognition accuracy of 99.75\% for GTSRB, 99.25\% for BTSC and 99.55\% for rMASTIF. In terms of latency and meeting the real-time constraint, the pre-processing time and inference time together do not exceed 1.3 ms per image. Not only have our proposed approach achieved remarkably high accuracy with real-time performance, but it also demonstrated robustness against traffic sign recognition challenges such as brightness and contrast variations in the environment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15127
PDF
-
How Language-Independent Are Emotional Attributes? A Study on Training Data Scaling and Cross-Lingual Generalization
Abstract
Current state-of-the-art Speech Emotion Recognition (SER) systems rely on lots of training data, which is available only for a few languages such as English. For low-resource languages, using a cross-lingual model or adapting it to the target language might be an alternative to training a mono-lingual model from scratch. However, it is not clear what constitutes a "low-resource", i.e. where model adaptation loses its edge over the mono-lingual approach. We investigate this topic by training and adapting several SER models on English and Mandarin data, focusing on the emotional attributes of arousal, valence and dominance. Our results show that, for arousal, model adaptation is beneficial even with two hours of data, while for valence 10-20 hours of adaptation material is required to match the performance of a mono-lingual model trained with 100 hours of data. This indicates that task-specific model adaptation may be an effective approach in low-resource speech emotion recognition problems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15059
PDF
-
MS-Exam-Gen: An Automatic Benchmark Construction Toolkit for Evaluating LLMs on Multiple Sclerosis-MRI Imaging Knowledge
2026-10-10 12:55:19Abdul Basit, Muhammad Abdullah Hanif, Muhammad ShafiqueAbstract
Biomedical large language model (LLM) evaluation requires auditable assessment of narrow, evolving, source-grounded subspecialty knowledge. Multiple sclerosis MRI (MS-MRI) provides a high-stakes textual-knowledge test case because correct reasoning requires current diagnostic criteria, standardized acquisition and reporting knowledge, longitudinal monitoring concepts, lesion morphology, and recognition of difficult mimics. We present MS-Exam-Gen, a reproducible framework for constructing and auditing a text-based multiple-choice question (MCQ) benchmark for MS-MRI knowledge; it does not evaluate direct MRI image interpretation. MS-Exam-Gen targets source-grounded criteria, protocols, reporting, and differential diagnosis. The framework combines expert-source indexing, exam-oriented topic induction, evidence-grounded MCQ generation, automated quality audits, a same-family consistency screen, and empirical calibration. From a 66-source corpus indexed into 4,289 retrieval chunks, the pipeline produced a locked 3,058-item candidate benchmark spanning 16 topics and 53 subtopics. Evaluation across 12 primary LLM endpoints yielded 36,696 item-level predictions and separated performance over a 42.8-percentage-point accuracy range (89.7% to 46.9%). Across these endpoints, 25.5% of items were missed by at least four. Post-generation audits showed that refreshed construction reduced measurable answer cues, while option-order testing showed that absolute MCQ scores remain position-sensitive. Generated construction labels remain metadata rather than validated psychometric categories. Because expert adjudication and full option-order counterbalancing remain future work, MS-Exam-Gen is not a clinically certified examination. It should be interpreted as an automatically filtered, source-grounded candidate benchmark and reproducible audit workflow for item-level and topic-specific LLM evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.06170
PDF
-
A Hybrid Kinematic GCN and Elastic Transformer for Efficient Indian Sign Language Recognition
2026-10-10 07:50:57Pushp Garg, Himangshu Sarma, Mrinmoy GhoraiAbstract
Sign Language Recognition (SLR) presents complex challenges due to variable signing speeds and spatial intricacies. Specifically, Indian Sign Language (ISL) requires precise modeling of its inherently bimanual nature and is bottlenecked by the scarcity of large-vocabulary benchmarks and the inability of standard models to handle irregular signing velocities. To address this, a structurally-aware hybrid framework for efficient, gloss ISL recognition is proposed. To minimize computational redundancy, an entropy-driven SVD sampler that dynamically extracts informative keyframes is used. Because this subsampling creates irregular physical time gaps, the proposed architecture employs a Continuous Dual Positional Encoding paired with a distance-aware Elastic Transformer to preserve natural signing rhythm. Spatially, a Kinematically-Conditioned Adaptive GCN explicitly models bimanual geometry using unified bone-joint features. To validate our framework, a 120-class, 9,453-video native ISL dataset is created. Augmented by Physical Node Dropout and ArcFace optimization to mitigate subject-specific memorization, our framework achieves a competitive 89.8% accuracy, establishing a strong baseline for complex sign language modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2610.14680
PDF
-
RASSG: Repair-Aware Semantic Survival Gating for Streaming Tool Execution
Abstract
Streaming speech assistants can launch tools before users finish speaking, overlapping execution with incoming speech to reduce user waiting time. However, subsequent self-corrections can invalidate apparently stable arguments, causing stale execution whose irreversible effects persist even after the final call is corrected. We propose Repair-Aware Semantic Survival Gating (RASSG) to jointly control tool launch and cancellation during streaming speech. RASSG launches a tool when three consecutive speech recognition results arrive with identical nonempty arguments, then combines calibrated argument invalidity risk with execution costs to decide cancellation at the last feasible opportunity before effects become irreversible. Evaluation on ReCAST, FDB-v3, and Audio2Tool uses a controlled execution clock with fixed tool runtimes and cancellation parameters. On ReCAST's prospective-repair subset, RASSG reduces the stale execution rate from LocalAgreement-2's 50.00% to 3.15%, with a mean delay of 3.676s across successful trajectories. The stale reduction also holds against every early-execution baseline on both public speech datasets. Ablations with identical initial launches support active cancellation, showing the value of controlling ongoing calls before their effects become irreversible. Code and data are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.14659
PDF
-
SpikCTU: A Compact Spiking Network with Adaptive Recurrent Computation for Speech Command Recognition
2026-10-10 05:32:07Li Jin, Jiang Wenbin, Chen Tao, Wen FeiAbstract
Spiking Neural Networks offer event-driven, energy-efficient computation for speech command recognition, yet most existing methods follow fixed computation paths, allocating redundant computation to easy samples while providing limited insight into how evidence evolves during inference. To address these challenges, we introduce SpikCTU, a compact spiking network with adaptive recurrent computation for speech command recognition. Specifically, a hybrid spiking embedding module preserves continuous input information alongside spike features to construct a fixed temporal memory. A shared Continuous Thinking Unit (CTU) repeatedly reads this memory using keys derived from spikes and continuous values, and updates a binary recurrent state with lightweight stage adapters. Furthermore, combining a fixed base prediction with accumulated corrections at each step enables learned aggregation over all steps or confidence-based early exit using only the predictions available so far. Experiments on three speech command recognition benchmarks show that SpikCTU achieves competitive accuracy with only 0.16--0.17M parameters, and the early exit strategy can substantially further reduce computational cost without compromising accuracy. In addition, trajectory and attention analyses reveal that recurrent steps enable error correction and progressively refine predictions. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.14594
PDF
-
Speech event detector: Timestamped detection of non-verbal vocalizations and background sounds for rich speech transcription
2026-10-09 18:49:55Ayush Kumar Bar, Promila GhoshAbstract
Automatic speech recognition produces words but drops the non-verbal content of a recording: the breaths, coughs, sighs and laughter of the speaker, and the horns, music or barking around them. We describe Speech Event Detector, a 5.8-million-parameter convolutional-Transformer model that outputs probabilities every 40 ms for 54 event classes (20 speaker vocalizations and 34 background sounds), together with post-processing that converts these probabilities into timestamped events and a procedure for merging the events into a Whisper transcript. The model is trained on material drawn from seven public datasets whose labels come in incompatible forms: single detected regions, free-text tags with timestamps, temporally strong ontology labels, symbols embedded in transcripts, isolated recordings and environmental recordings. We unify them using rule-based label mapping, recover timestamps for transcript-embedded labels through CTC forced alignment, locating 6,360 of 8,620 sounds, and combine about 168 hours of real annotated training recordings with synthetic mixtures and augmentation using real background noise. Per-class thresholds for two operating profiles are tuned on real held-out recordings, and performance is estimated using two-fold cross-validation. On whole held-out recordings from four datasets, considering the 48 classes with at least ten held-out events, the sensitive profile detects an average of 49 percent of a class's events, covering 67 percent of all 9,367 events, at a macro precision of 0.30. The balanced profile achieves a macro recall of 0.37 at a precision of 0.36, with macro event F1 scores of 0.32 and 0.33, respectively. The detector runs about 39 times faster than real time on eight CPU threads.
Abstract (translated)
URL
https://arxiv.org/abs/2610.14232
PDF
-
Event-based Action Recognition by Pre-Training on Multi-Frame Representations
2026-10-09 17:05:40Emma Norrby, Tomas Wilkinson, Per Nyblom, David GustafssonAbstract
Action recognition is a crucial task in domains like robotics, patient monitoring, or surveillance. Recently, event-based action recognition has attracted much attention due to the event camera's ability to capture fast motions and its improved privacy over conventional vision cameras. While frame-based event representations work well for short event sequences, their discriminative ability declines sharply with longer and more complex event sequences. In this work, we introduce a multi-frame representation that greatly improves recognition performance over its single-frame counterpart. We adopt a masked auto-encoding framework to pre-train a Vision Transformer using a sparsity-aware masking algorithm and token selection mechanism to improve downstream performance and control computational complexity. We also introduce multiple mask tokens for the decoder with a position-aware attention mechanism, leading to further improved performance. Our proposed method shows impressive performance for challenging long-duration and complex event sequences, yielding state-of-the-art performance on THU-EACT-50 CHL and DailyDVS-200.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13856
PDF
-
Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR
2026-10-09 16:19:43Katsumi Ibaraki, David ChiangAbstract
Data augmentation is standard practice for low-resource automatic speech recognition (ASR), but its benefits are almost always reported as aggregate error rates, leaving open why and when a method helps. On four low-resource languages and English at five data sizes, we cross two augmentations that modify existing audio (speed perturbation and SpecAugment) with two that modify text transcriptions and synthesize audio from it. We analyze errors at the phoneme level and find that they help for complementary reasons. SpecAugment has the most reliable aggregate improvements, but increases tone and palatalization errors, whereas text-based methods introduce consonant insertions; in combination, each reduces the errors the other introduces. This complementarity is predictable. Tone and palatalization are each signaled by a single acoustic property and occur least frequently in training (lowest training exposure), and text-based methods that flatten word frequency raise their frequency by 37--38%, reversing those errors while further improving aggregate error. The improvement from combining the methods exceeds the sum of their individual improvements; the superadditivity vanishes by 100 hours, limiting the complementarity to the low-resource regime. Where specific error types matter, we recommend selecting augmentation by training exposure and acoustic properties, both measurable before any training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13807
PDF
-
Enhancing Speech Recognition through Text-to-Speech and Voice Conversion Augmentation
2026-10-09 14:33:36Yunus Emre Ozkose, Ali HaznedarogluAbstract
Given the challenges associated with obtaining large volumes of real-world audio, the advancement of Automatic Speech Recognition (ASR) systems increasingly depends on synthetic data. This study focuses on the call center-banking domain, providing a targeted analysis of ASR models in this context. We evaluate real and synthetic datasets, using Word Error Rate (WER) and Character Error Rate (CER) as metrics, and employ a speech quality model to assess the impact on ASR performance. Our research compares Text-to-Speech (TTS) and advanced voice conversion methods, including KNNVC, Seed-VC, and Vec2Wav2, revealing significant improvements in speech quality and ASR accuracy, particularly with Seed-VC. Additionally, our domain-specific experimentation provides insight into the unique challenges and opportunities that arise when applying ASR technologies to industry-relevant settings. This highlights the potential of voice conversion technologies to enhance ASR systems, guiding future research in diverse linguistic scenarios, and paving the way for the broader application of ASR innovations across various fields.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13662
PDF
-
CUBE: Class-conditioned Unknown Boundary Evidence for Open-Set Insect Species Recognition
2026-10-09 13:57:13Hao Tan, Qimin Zhang, Zhe Xiao, Zekai Zuo, Wanting Liu, Jinghui QinAbstract
Open-set insect species recognition faces significant challenges when deployed in real-world biodiversity scenarios, particularly when encountering unknown species that are visually close to known training classes. Unlike generic out-of-distribution samples, fine-grained unknown insects are often not visually anomalous. They instead tend to appear near the decision boundary of specific known species, leading to unreliable closed-set predictions. To address these challenges, we propose \textbf{Class-conditioned Unknown Boundary Evidence (CUBE)}, a novel evidence-based framework that models unknownness around each known species rather than as a single global unknown class. Our key idea is to evaluate a test sample relative to the known species it most closely resembles, enabling local rejection for visually confusable unknown insects. CUBE learns class-conditioned boundary evidence from auxiliary species, preserves auxiliary species as shadow references during inference, and incorporates taxonomic candidate calibration to verify biological plausibility. When ecological metadata is available, we further introduce CUBE-E, which adds a lightweight location-consistency term without modifying the visual backbone. Experiments on the Open-Insect C-America benchmark show that CUBE achieves superior performance, outperforming state-of-the-art baselines with 95.8\%, 98.7\%, and 99.1\% AUROC on local, non-local, and non-moth unknown splits, respectively, while maintaining 94.9\% closed-set accuracy. With ecological metadata, CUBE-E further improves the results to 96.0\%, 99.7\%, and 99.5\% AUROC with 95.2\% closed-set accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13610
PDF
-
Lossless Inference Acceleration for ASR via EAGLE-Style Speculative Decoding
2026-10-09 12:32:09Sen Zhang, Xianghu Yue, Yiming Chen, Wenhuan Lu, Jianguo Wei, Haizhou LiAbstract
Autoregressive Transformer and Conformer models have achieved state-of-the-art performance in automatic speech recognition (ASR). However, their sequential token generation mechanism imposes a significant bottleneck during decoding, resulting in substantial inference latency. While speculative decoding has emerged as a promising lossless acceleration technique, existing ASR-oriented approaches either suffer from low draft acceptance rates due to suboptimal draft quality or rely on specially designed external draft models, which limit their generality and practicality. To overcome these limitations, we propose EAGLE-ASR, a novel framework that accelerates ASR inference via EAGLE-style speculative decoding while strictly preserving lossless output quality. Specifically, we introduce Speech-Draft, a lightweight autoregressive module that serves as a universal draft model by jointly leveraging encoder acoustic features and hierarchical decoder representations from the target ASR model. Furthermore, we adopt a multi-step generation strategy with self-distilled data to train the Speech-Draft, enabling it to better approximate the target model's output distribution and maintain causal consistency during multi-token generation. Extensive experiments on representative Whisper and Conformer AED models demonstrate that EAGLE-ASR achieves significant lossless speedups of up to $1.9\times$ and $2.4\times$, respectively, consistently outperforming existing speculative decoding baselines for ASR. Our proposed framework further generalizes effectively to multilingual ASR and speech translation tasks, establishing EAGLE-ASR as a practical and universally applicable solution for accelerating modern ASR systems without compromising recognition accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13506
PDF
-
When MLLMs miss what humans read: diagnosing and learning to read squint text
2026-10-09 12:02:22Chen Peng, Shan Huang, Jianbo Huang, Linrui Qin, Qibo Sun, Mengwei XuAbstract
Multimodal LLMs can fail to read text embedded in an image's coarse structure (text a human recovers by squinting) and report that no text is present. We name this class Squint Text and study it as a recognition deficiency, motivated by cases from a production moderation pipeline. We introduce SquintBench, comprising 1076 production-derived moderation images, and SquintCtrl, a controlled synthetic suite for mechanism diagnosis. Frozen-weight analysis shows that hidden text leaves a coarse signal while glyph identity is weakly represented; identity becomes substantially more accessible when the correct spatial regions are supplied, implicating spatial selection as a major bottleneck. Suppressing high-frequency content also improves reading at a fixed visual-token budget, while visual token count may also contribute. These findings motivate Squint OPSD: a frozen teacher receives a downscaled view and the ground-truth transcription as privileged context, and its token-level distributions supervise a student along on-policy trajectories. At inference, the student reads the original image alone. Squint OPSD reaches 88.61 ANLS on SquintBench, versus 26.50 for the unadapted backbone, 24.44 for the best general-purpose model on the original view, and 68.60 at best for an off-the-shelf model under a downscaled view. These results substantially narrow the gap between available visual evidence and its generated read-out without auxiliary views at inference.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13465
PDF
