Speech_Recognition
-
Linguistic Distance Segregates Latent Representations in Automatic Speech Recognition Systems
2026-08-31 14:16:21Ting-Hui Cheng, Line Katrine Harder Clemmensen, Sneha DasAbstract
While automatic speech recognition (ASR) models have achieved remarkable improvements in recent years, performance disparities persist across different speaker populations. One such disparity is for speakers whose first languages (L1) are from families distant from English. This paper investigates the relationship between first language background and English ASR performance. Through empirical analysis, we observe that the correlation between speakers' L1 distance and ASR error rates yields a systematic effect on English Speech, with its strength varying across datasets and models. This association is statistically significant in a follow-up analysis accounting for dataset-level variation in Tweedie mixed-effects models ($p<0.001$ across evaluated models). In addition, analysis of the latent space reveals a L1-based spatial segregation across deeper acoustic layers in the majority of evaluated architectures
Abstract (translated)
URL
https://arxiv.org/abs/2608.30853
PDF
-
Conjoint Audio-to-Spikes Encoding and Processing for Efficient Neuromorphic Speech Recognition
2026-08-31 13:47:14Valentin M. Meunier, Am\'elie Gruel, Pierre Lewden, Adrien F. Vincent, Sylvain Sa\"ighiAbstract
Obtaining data from neuromorphic sensors and processing it with Spiking Neural Networks is a promising solution to lower the energy cost of artificial intelligence. The current rarity of natively neuromorphic datasets promotes the development of software tools to translate input sensory data into spikes. However, highly bio-mimetic simulators can be challenging to implement on digital hardware. In this work, we evaluate the neuromorphic encoding and subsequent classification of audio into spikes using a non-learnable, high-level, programmable encoder targeting hardware implementation on FPGA. We quantify the pipeline's efficiency with hardware-agnostic metrics based on the quantitative spiking activity. Our study focuses on the simultaneous optimisation of encoder and classifier: the first provides efficient and informative data so that the latter achieves a better performance with an overall lower energy cost at learning and inference. This work introduces the first end-to-end neuromorphic spike-encoding and evaluation of the TIMIT dataset. Our simple feedforward network reaches a classification accuracy of 99.77% on a spike-encoded Heidelberg Digits, overcoming the neuromorphic state of the art on this benchmark dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30792
PDF
-
Closing the Verification Loop: Self-Check Captioning for Long-Paragraph Detailed Audio Captioning
2026-08-31 12:50:10Fengji Ma, Yan Rong, Xu Li, Chen Zhang, Pengfei Wan, Li LiuAbstract
Long-paragraph detailed audio captioning, which requires dense and transcript-faithful descriptions of fine-grained audio content, remains unsolved for current audio-visual multimodal language models. We attribute this failure to two structural problems. The first is data poverty, as no public corpus jointly provides long clips, paragraph captions, and verbatim-transcript fidelity. The second is generation-mode failure, evidenced by a 44.8 to 46.4 percentage-point gap between right-audio and shuffled-audio multiple-choice question (MCQ) accuracy. We address both within Self-Check Captioning (SCC), a unified framework that instantiates audio-grounded question answering as the verification primitive at every lifecycle stage. SCC yields three artifacts. Long-paragraph Audio Caption 50k (LACap-50k) is a 50,222-clip audio-visual corpus with 491.5-word captions and a post-hoc automatic speech recognition (ASR) audit. Layer-Curvature Supervised Fine-Tuning (LC-SFT) is the first on-policy supervised fine-tuning method to weight tokens by intermediate-layer evidence, motivated by our identification of Late-Layer Semantic-Entropy Collapse (SEC). SCC-Verifier arbitrates among caption rollouts via audio-grounded self-answering at inference. Across multiple benchmarks, our system attains state-of-the-art among open-source captioners and is competitive with proprietary baselines. We release LACap-50k to fill the resource gap for long-paragraph detailed audio captioning research.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30713
PDF
-
TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models
2026-08-30 19:49:21Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Utathya Aich, Ramani Duraiswami, Dinesh ManochaAbstract
Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify. Despite being essential for downstream tasks like speech recognition and dense audio captioning, timestamping remains a key limitation of most LALMs. We present TEMPO (Temporally-grounded Multi-task Post-training), the first unified model to handle audio, speech, and music timestamping tasks. Our core contribution is a supervised fine-tuning (SFT) stage built on three innovations: atomic timestamp tokens, a time-aware projector that injects sinusoidal wall-clock encodings into audio frame embeddings, and a distance-aware Gaussian loss. Our training is based on a synthetic-to-real curriculum. We further introduce, to our knowledge, the first application of reinforcement learning to unified audio timestamping, using GRPO with verifiable temporal rewards that directly optimize the evaluation objectives. Rather than serving as the primary source of performance gains, GRPO acts as a refinement stage on top of the SFT checkpoint, providing modest additional improvements. To support this work, we build a training dataset containing 119K samples and an evaluation benchmark containing 10K samples, drawn from established corpora across five tasks. On this benchmark, TEMPO outperforms Audio Flamingo Next and Qwen3-Omni, two state-of-the-art LALMs explicitly trained on timestamped data. Experiments confirm that SFT delivers most of these gains, with GRPO providing consistent but moderate refinements.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29999
PDF
-
Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages
2026-08-29 12:52:03Kuan-Tang Huang, Cheng-Yeh Yang, Chien-Chun Wang, Hung-Shin Lee, Hsin-Min Wang, Berlin ChenAbstract
Low-resource ASR remains difficult because scarce transcripts provide limited supervised evidence for target-side generation. To address this gap, we propose SAMA-ASR, a lightweight adapter mechanism that augments the decoder with semantic anchors from auxiliary translations and an acoustic anchor from speech; in principle, the mechanism can be applied to similar encoder--decoder multitask speech models. Through cross-modal adaptation, SAMA-ASR conditions decoder states on translation-derived semantic embeddings and a speech embedding, combining utterance-level meaning with speech-grounded evidence before token prediction. At evaluation time, these semantic anchors can be generated automatically by an upstream speech-to-text translator rather than supplied as oracle translations. Experiments on two 30-hour datasets covering the low-resource Sinitic varieties Taiwanese Hokkien and Hakka show that SAMA-ASR improves over acoustic, prior prompt-based, and semantic-only translation-guided baselines and remains effective in practical automatic semantic-anchor settings; translator-capacity analyses show that useful semantic anchors can be produced by a compact ST model.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29239
PDF
-
VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition
2026-08-28 22:23:42Tyler Baumgartner, Brandon Tai, Lisa Kaelin-Martin, Candice Fan, Luc Debaupte, Bill Wang, Yi ZhongAbstract
Automatic speech recognition (ASR) systems are commonly evaluated with word error rate (WER), yet many voice workflows depend on exact written values for identifiers, paths, and measured quantities. A transcript can appear fluent and achieve low WER while corrupting a value that a downstream system must parse, store, or execute. We introduce VoiceCodeBench, a benchmark for evaluating exact structured-token recovery in English ASR. It contains 300 human-recorded workplace segments spanning eight workflow domains and 1,482 audited target entities across 26 entity types, each with a canonical written form recoverable from the audio. Under a raw-audio-only protocol, systems receive audio bytes without additional context or metadata. Alongside WER, we evaluate Canonical Token/Entity Match (CTEM), Task Success Rate (TSR), and per-type exact recovery. Across 12 baseline ASR systems, lower WER generally corresponded to better structured-token recovery but did not fully determine it: Spearman correlations were -0.73 for both WER versus CTEM and WER versus TSR. The strongest baseline by TSR reached only 68.7%, leaving nearly one third of recordings with at least one unrecovered workflow-critical value. These results show that entity-sensitive metrics are needed to assess whether ASR output preserves exact values that production systems must parse, route, store, compare, or execute.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28916
PDF
-
When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI
2026-08-28 16:55:32Sihan Jia, Oliver LemonAbstract
We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that ASR errors can lead to harmful instructions being accepted and executed by EAI models, thereby reducing safety. We simulate ASR errors and combine them with existing safety benchmarks (SafeAgentBench and POEX) to evaluate how different errors affect embodied AI safety. We find that some of them preserve semantic structure but increase harmful ambiguity, while others weaken the model refusal behaviour and allow unsafe plans to be generated and executed. We show that in some cases automatic correction of ASR errors can reduce the risk, but this is not always effective. Overall, we show that ASR errors lead to significant safety risks for embodied AI.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28518
PDF
-
Auditing Generative Audio Calls for Known-Task Audio-LLM Evaluation
2026-08-28 01:33:47Mengzhe GengAbstract
Speech and audio LLMs are often evaluated by asking whether a waveform prompt beats an automatic speech recognition (ASR) transcript. For known closed-set tasks, that comparison conflates two factors: access to acoustic evidence and the need to call a generative audio model. We evaluate this distinction as a controlled call-decision problem. For each example, a policy chooses among keeping a transcript label, using encoder evidence from Contrastive Language-Audio Pretraining (CLAP), Audio Spectrogram Transformer (AST), or WavLM, and calling Qwen2-Audio, Qwen2.5-Omni, or MOSS-Audio; the decisive ablation removes all generative actions while keeping the selector and development protocol fixed. On VocalSound, transcripts reach 0.296 accuracy, so waveform information is needed. Yet supervised CLAP and WavLM controls reach 0.850 and 0.854 with no generative audio calls. A selector with generative actions reaches 0.925 accuracy using 12.5% calls, compared with 0.921 for the matched no-call selector (paired difference 0.004; 95% CI [-0.025,0.033]). Agreement and stacking features improve weaker selectors but do not beat the strongest no-call control. For known-task endpoint claims, the relevant quantity is the marginal value of the generative call after transcript and encoder evidence have already been used.
Abstract (translated)
URL
https://arxiv.org/abs/2608.27817
PDF
-
Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts
2026-08-27 21:55:50Saman Rahbar, Xiliang Zhu, Irvin Cardoza, David RossouwAbstract
In contact centers, real-time agent-assist tools determine, for each of many predefined topics, whether a live customer utterance is relevant and display a coaching card to the agent when it is. The input is noisy and challenging: ASR(Automatic Speech Recognition) transcripts of spontaneous phone conversations, which can be unclear, repetitive, and mostly lack punctuation. To systematically study this real-world task, we curate a human-annotated topic-utterance judgments dataset sourced from real call-center transcripts. We compare three types of matchers: a regex-based baseline, zero-shot sentence embedding encoders, and Gemini-based LLM matchers. In addition, two types of topic representations are studied in our benchmark:keyphrases and natural language description. Our empirical experiments highlight the superior performance of lightweight LLM matchers over embedding and regex models when equipped with natural language descriptions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00330
PDF
-
Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition
2026-08-27 12:36:09Yuta Kurotaki, Shusuke Yamakoshi, Reitaro Yoshida, Yutaka Isoda, Tamami Takano, Yuji Isano, Yusuke Miyake, Kentaro Kuribayashi, Hiroki OtaAbstract
Silent speech recognition (SSR) provides an alternative communication pathway in the absence of audible speech. However, conventional approaches are limited by the need for constant facial attachment, privacy concerns, and unstable signal acquisition. Here, we propose a soft, active electromyography (EMG) interface that enables word-level SSR using machine learning. Worn on the hand, the device uses a fingertip electrode that can be positioned near the lips to acquire EMG signals only when needed. The interface integrates liquid metal (LM) interconnects, transparent flexible printed circuit (FPC) electrodes, and elastomer encapsulation to ensure high mechanical stability during finger motion. A deep neural network trained on these stable signals achieved a mean accuracy of 97.2 $\pm$ 1.3% across three subjects in classifying a 30-word vocabulary, demonstrating robust linguistic discrimination. Furthermore, real-time drone control validates the practicality of this approach in noisy and privacy-sensitive environments where conventional voice recognition fails. This study highlights the potential of soft, wearable EMG systems as secure and intuitive human-machine interfaces.
Abstract (translated)
URL
https://arxiv.org/abs/2608.27048
PDF
-
Direct or Mediated? Task-Dependent Audio Information Routing in Large Audio Language Models
2026-08-27 12:12:26Yizhou Zhang, Wangjin Zhou, Xin Gu, Yichi Wang, Wei Tan, Yi Zhao, Zhi Gong, Keisuke Imoto, Tatsuya KawaharaAbstract
Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio understanding tasks. However, they are typically evaluated on single, coherent audio segments, leaving their behavior under less familiar input configurations underexplored. We study this issue through a controlled setting in which two audio segments are concatenated into a single input. Across multiple LALMs, we observe a striking task-dependent robustness gap: automatic speech recognition (ASR) remains comparatively stable, whereas audio question answering (AQA) degrades substantially. To investigate the mechanisms underlying this disparity, we analyze how audio information is routed through LALM decoders using layer-wise attention knockout. The results reveal distinct task-dependent pathways. ASR relies primarily on direct retrieval from audio tokens by answer tokens, whereas AQA depends more strongly on a mediated route in which audio information is first integrated into prompt tokens and subsequently accessed during generation. We further probe prompt-token representations under audio concatenation and find that task-relevant audio attributes remain readily decodable, particularly in middle and later decoder layers, even when AQA performance deteriorates sharply. This dissociation indicates that the failure cannot be explained by complete loss of audio information from the decoder states and is instead consistent with a downstream bottleneck in retrieving or utilizing prompt-mediated information during answer generation. Together, our findings reveal task-dependent audio information routing in LALMs and highlight information utilization as a potential limitation on their generalization.
Abstract (translated)
URL
https://arxiv.org/abs/2608.27026
PDF
-
Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study
2026-08-27 06:53:32Zhen Wang, TianRui Wu, RongQi Han, Hao Wu, Wei LiangAbstract
Synthetic speech provides scalable supervision for automatic speech recognition (ASR), but its benefit depends on the selected texts, reference speech, and amount of synthesized data. We present a unified phoneme-based TTS-to-ASR augmentation pipeline built around a multilingual TTS model trained from scratch using the F5-TTS architecture with language-ID conditioning. The pipeline combines language-specific grapheme-to-phoneme conversion, reference-speech filtering, candidate-text selection, synthesis, and matched ASR continuation. We further propose phoneme-frequency-guided selection (PFGS), which ranks candidate sentences using phoneme frequencies estimated from real ASR training labels. Experiments with separate monolingual ASR systems for Arabic, French, Italian, and Portuguese span 13 test sets. Across the synthesis-scale sweep, random augmentation improves over matched real-only continuation on 11 test sets. Under a nominal 60% synthesis budget, PFGS improves over real-only training on 12 test sets and over random selection on 9. Its largest relative word error rate (WER) reduction against random selection is 19.3%. With target texts and synthesis counts fixed, reference-speech filtering reduces absolute WER by 0.29 and 0.59 points on Italian and French Common Voice, respectively. These results identify synthesis scale, candidate-text content, and reference quality as important control variables in TTS-based ASR augmentation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.26697
PDF
-
AfriSwitch: A Benchmark for In-the-Wild African Code-Switched Speech Recognition
2026-08-26 22:20:58Gabrial Zencha Ashungafac, Busayo Awobade, Tobi OlatunjiAbstract
Code-switching is pervasive in bilingual African conversation, yet most ASR systems assume monolingual input and are evaluated on curated monolingual benchmarks. We present AfriSwitch, a 61.36-hour human-transcribed benchmark of in-the-wild code-switched speech spanning 16 African languages and language varieties, released with switch-level English span tags, perutterance Code-Mixing Index (CMI), and switch-point counts. Corpus statistics show that mixing behaviour varies widely across African languages along two largely independent axes: how often speakers alternate, and how balanced the mixture is. No single scalar captures how code-switched a language is. Benchmarking five open and commercial multilingual ASR systems zero-shot yields word error rates far above published monolingual figures for the same languages, with the best system averaging 35.93% WER and no system falling below 24% on any language. Africa-targeted training, not model scale or nominal language coverage, best predicts performance.
Abstract (translated)
URL
https://arxiv.org/abs/2608.26434
PDF
-
Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary Study
2026-08-26 17:29:47Leonardo Duart, Tiago Fonseca, Thiago Chac\'onAbstract
Automatic Speech Recognition (ASR) technologies have achieved remarkable performance in recent years through the use of large multilingual foundation models. However, most advances remain concentrated on high-resource languages, while indigenous languages continue to suffer from a lack of speech resources and language technologies. This work presents a preliminary study on the adaptation of Whisper for Automatic Speech Recognition in Baniwa, an indigenous Arawakan language spoken in Brazil, Colombia, and Venezuela. The experiments were conducted using a corpus of 1,373 manually transcribed recordings obtained from a linguistic documentation project. The corpus contains approximately 0.54 hours of speech and consists primarily of isolated words and short elicited utterances. The Whisper Small model was fine-tuned using supervised learning and evaluated using Word Error Rate (WER) and Character Error Rate (CER). The best model achieved a WER of 37.5% and a CER of 7.45%, demonstrating that multilingual foundation models can be successfully adapted to extremely low-resource indigenous languages. The results establish an initial baseline for Baniwa Automatic Speech Recognition and provide a foundation for future research involving larger datasets, language-specific adaptation strategies, and post-processing techniques.
Abstract (translated)
URL
https://arxiv.org/abs/2608.26060
PDF
-
Lost but not erased: Finding traces of a forgotten language in neural speech models
2026-08-26 16:32:41Peter Plantinga, Charlotte Moore, Peter W. Donhauser, Krista Byers-Heinlein, Denise KleinAbstract
International adoptees retain phonological traces of a birth language they can no longer speak or comprehend, a persistence typically attributed to a biologically-timed critical period. We asked whether it could instead reflect the ordinary dynamics of learning, using automatic speech recognition models that simulate the international adoptee experience without maturational confounds. Models were trained on one language and then abruptly switched to a second. We found that traces of the first language persisted throughout second-language training, but mainly in the lowest, pre-phonemic layers. These traces were functional, as models with early exposure re-learned their lost first language 14% faster than naive models; this advantage held even against models adopted early from a related language and disappeared when the earliest layers were substituted from a non-adopted model. We argue that these critical-period effects reflect entrenchment of foundational representations rather than a maturational loss of plasticity, and that experience plays a central role in critical periods in language acquisition.
Abstract (translated)
URL
https://arxiv.org/abs/2608.25976
PDF
-
Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study
2026-08-26 09:36:48Thibault Ba\~neras-Roux, Shashi Kumar, Driss Khalil, Sergio Burdisso, Petr Motlicek, Shiran Liu, Mickael Rouvier, Jane Wottawa, Richard DufourAbstract
Automatic Speech Recognition (ASR) is typically evaluated using Word Error Rate (WER), which poorly reflects semantic similarity. While embedding-based metrics correlate better with human judgments, the respective roles of encoder and decoder-based Large Language Models (LLMs) remain underexplored. This paper presents a comparative study of both families for ASR evaluation. We analyze BERTScore and SemDist across different LLMs, layers, and pooling strategies, showing that both metrics can achieve strong correlation with human judgments when properly configured. For decoder models, we investigate generative LLMs in two settings: pairwise hypothesis selection via prompting and direct qualitative error classification. Our results show that encoder-based metrics remain highly competitive, while generative LLMs perform strongly in hypothesis comparison and improve the interpretability of ASR evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.25574
PDF
-
Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition
2026-08-26 08:25:15YoungChae Kim, Da-Hee Yang, Joon-Hyuk ChangAbstract
Large language model (LLM)-based audio-visual speech recognition (AVSR) systems are robust under noise. Contrastive decoding (CD), originally introduced to stabilize LLM generation by contrasting a weaker model against a stronger one at inference time, adjusts predictions without additional training. In this work, we apply CD to AVSR by contrasting audio-only conditioning with full audio-visual conditioning within the same underlying model. However, using a fixed contrastive strength introduces a trade-off across noise levels: stronger intervention helps under severe noise but may over-correct reliable predictions in clean conditions. We propose reliability-aware scaling of CD for AVSR. Instead of using a fixed strength, we adaptively modulate the contrastive influence at each token based on reliability signals derived from attention dynamics and inter-model predictive divergence. Experiments on LRS3 show consistent improvements across clean and low-SNR conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2608.26213
PDF
-
Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors
Abstract
Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically test whether two extensions to standard retrieval-augmented generation (RAG), entity-graph linking and iterative reformulation, absorb or amplify these errors. Using four English accents synthesized through neural TTS, we evaluate four RAG configurations on three multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA and MuSiQue) against a clean-text oracle. Although the structurally richer configurations generally retain higher absolute F1 under ASR input, both extensions amplify the error: the F1 gap from clean text to the highest-WER accent is 36-67% larger under their combination than under naive dense retrieval, on all three benchmarks. The dominant failure mode is corruption of one or more query entities, accounting for 87-96% of degradation cases on 2WikiMultiHopQA across all four methods. Two lightweight surface-form mitigations leave most of the gap intact, indicating that downstream retrieval structure amplifies remaining entity errors. We release code and data at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2608.22872
PDF
-
DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios
2026-08-24 04:37:28Bingshen Mu, Xian Shi, Xiong Wang, Zhifang Guo, Ting He, Xize Cheng, Yu Xi, Jin Xu, Lei XieAbstract
Multi-speaker automatic speech recognition (MSASR) aims to jointly predict content transcriptions, speaker identities, and timestamps, thereby addressing the key question of "who spoke what and when" and holds substantial practical value in real-world multi-speaker scenarios. However, MSASR still encounters considerable challenges in the presence of fast turn transitions, overlapping speech, and complex, diverse multi-speaker scenarios. In this work, we propose DiaScriber, an end-to-end multi-speaker diarization and transcription model built on a speech large language model. We first construct diverse data pipelines to cover a wide variety of multi-speaker scenarios and their complexities, including validation and refinement, turn-transition and overlapping-speech simulation, and multimodal annotation. Furthermore, DiaScriber is developed based on the pretrained version of Qwen3.5-Omni through a three-stage training strategy involving continual pretraining, supervised fine-tuning, and reinforcement learning. Experiments show that DiaScriber achieves superior performance over comparison methods across extensive multi-speaker scenario test sets and demonstrates outstanding generalization ability in unseen multi-speaker scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2608.22796
PDF
-
Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026
2026-08-23 10:11:17Jinxing Zhou, Suiyi Zhao, Yanghao Zhou, Ruohao GuoAbstract
Speech-guided referring video object segmentation aims to recover the mask tracks of objects specified by a spoken motion description. Here, speech carries a linguistic instruction rather than acoustic evidence from a sounding object, so a solution must connect speech recognition, motion-centric temporal grounding, mask tracking, and explicit no-target handling. We introduce Speech2MaskTrack, our approach for the MeViS-Audio track of the 8th LSVOS Challenge. Speech2MaskTrack transcribes the spoken query and compiles it into structured constraints over category, count, direction, interaction role, and temporal phase. SAM3.1 enumerates multiple instance tracks, which TRACE ranks using complete-trajectory motion and relation evidence. A frozen lexical presence gate may suppress the ranked SAM3.1 base prediction. When the gate predicts that a target is present, an available full-expression-conditioned SaSaSa2VA track replaces the SAM3.1 mask. Only outputs that remain empty enter GPT-assisted recovery, which invokes SaSaSa2VA again under query- and mask-level verification. Speech2MaskTrack achieved second place in the official challenge ranking.
Abstract (translated)
URL
https://arxiv.org/abs/2608.22337
PDF
