Speech_Recognition
-
Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition
2026-09-09 16:14:29Rishabh Jain, Aristeidis Papadopoulos, Zhaofeng Lin, Naomi HarteAbstract
Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the complexity of natural conversation, which involves overlapping speech, spontaneous turn-taking, unscripted vocabulary and variable acoustic conditions. To shift the field toward realistic dialogue, we introduce Candor-LR, a conversational benchmark derived from the CANDOR corpus of 1,656 natural dyadic videoconferences. Our custom data preparation pipeline yields 713.5, 10.1, and 60.1 hours of training, validation, and test data, respectively. Evaluating pretrained AVSR models on Candor-LR reveals that audio-only accuracy drops sharply compared to LRS3, but visual cues compensate effectively, driving much larger performance gains on Candor-LR than on LRS3. Furthermore, training on this corpus significantly improves cross-domain robustness under both clean and noisy conditions, as its realistic conversational data captures broader audio-video features. We open-source our pipeline to ensure reproducibility, establishing Candor-LR as a challenging benchmark for conversational AVSR.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10394
PDF
-
Qwen-Audio-3.0-ASR Technical Report
2026-09-09 11:59:55Chuanmeng Bian, Daren Chen, Peixin Chen, Zhigao Chen, Zhiyun Fan, Zhifu Gao, Bo Gong, Qing Gu, Jiajun He, Yawei Hu, Yunjie Ji, Jingbei Li, Xiangang Li, Xu Li, Zengxi Li, Zheng Li, Chengdong Liang, Baiji Liu, Ying Liu, Bin Ma, Yiping Peng, Yuezhang Peng, Zhendong Peng, Yu Pu, Yang Shi, Xin Shu, Jian Tang, Biao Tian, Peiyao Wang, Tianzi Wang, Wen Wang, Wupeng Wang, Cheng Wen, Yuzhong Wu, Zijian Xia, Yunchong Xiao, Nan Yang, Jianwei Yu, Jixing Yu, Binbin Zhang, Lei Zhang, Sitong Zhao, Guangdong Zhou, Yuan Zhou, Jianheng ZhuoAbstract
In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility remains a persistent challenge, particularly in handling diverse regional dialects, dynamic entities and hotwords, long-range contextual information, and disfluent spontaneous speech. In this report, we present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address these production demands through a unified, instruction-following framework. The model is built upon the Qwen backbone, and is trained on tens of millions of hours of large-scale speech data. Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions. Beyond multilingual and dialectal recognition, the model provides production-oriented capabilities including industry-domain entity recognition, hierarchical hotword customization, native single-pass transcription polishing, and long-audio contextual modeling. We further develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications. Extensive evaluations on Chinese, English, multilingual, and real-world industrial test sets demonstrate state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions, with strong performance relative to leading commercial and proprietary systems including GPT-4o Transcribe and Gemini 3.1 Pro.
Abstract (translated)
URL
https://arxiv.org/abs/2609.07549
PDF
-
Source-Adaptive Data Curation for Bilingual NVV-Aware ASR
2026-09-09 09:19:15Yuang Cao, Qirui Zhan, Jingbin Hu, Ziyu Zhang, Yunxiang Chen, Houdun Liu, Shuo Feng, Bengu Wu, Lei Xie, Liumeng XueAbstract
Nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, convey affective and interactional information that conventional automatic speech recognition (ASR) systems often discard. We present a bilingual Mandarin-English system for Track 1 of the NVVSpeech Challenge at ISCSLP 2026, which requires joint transcription of lexical content and 16 NVV categories at their transcript-relative positions. Our NVV-Aware Whisper adapts Whisper-medium through checkpoint-compatible vocabulary remapping, enabling lexical tokens and inline NVV tags to be decoded within a unified autoregressive sequence without expanding the vocabulary. To provide reliable and diverse supervision, we further introduce a source-adaptive data curation strategy that refines public NVV corpora through acoustic augmentation and multimodal LLM filtering, while mining spontaneous NVVs from in-the-wild media through automated preprocessing and annotation. Under the official bilingual evaluation protocol, the proposed system improves final score from 33.32 to 53.61, with ablations confirming the complementary benefits of the proposed data-curation components.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09929
PDF
-
Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services
2026-09-09 08:45:20Yonghyun Jun, Jimin Lee, Hwan Chang, Dongho Shin, Seolah Kim, Hwanhee LeeAbstract
Automatic Speech Recognition (ASR) technology is fundamental to customer service automation and large-scale transcription. However, even advanced ASR models exhibit inevitable errors in complex real-world environments such as call center conversations. When privacy restrictions preclude audio access, error correction must rely on text-based post-editing. Existing text-only approaches face significant challenges in low-resource languages, mainly due to a critical scarcity of annotated corpora and tailored correction methodologies. For Korean, this resource gap is particularly pronounced, as existing resources are predominantly designed for ASR training rather than text-based error correction. To address this, we introduce DasanCallDial, the first large-scale Korean benchmark dataset specifically curated for dialogue-level ASR error correction. Derived from genuine call center interactions, it comprises 1,974 dialogues with 115,460 utterances. Leveraging this resource, we propose Detector-Gated Contextual Span Correction (DCSC), a text-only post-editing framework for error-sparse Korean speech recognition transcripts. DCSC combines an encoder-based detector that first performs token-level error detection, followed by a language model-based corrector trained to rectify fine-grained span-level errors. Additionally, we employ dialogue-level context augmentation to enable the model to leverage discourse history for disambiguation. By employing multi-level granularity, our method achieves state-of-the-art performance, effectively overcoming the limitations of general LLMs in low-resource settings.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09889
PDF
-
$S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants
2026-09-09 08:06:28Heyang Liu, Jiayi Huang, Wenyang Xiao, Ziyang Cheng, Lixin Zhang, Zhen Liu, Miao He, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu WangAbstract
The advance of multimodal large language models (MLLMs) has fundamentally reshaped the paradigm of human-computer interaction, especially speech interaction models capable of seamless conversations. Despite remarkable performance as general voice assistants, their performance in specialized domains remains underexplored, particularly in scientific areas. Scientific interactions introduce formidable challenges, involving rare technical terminology, spoken norms of abbreviations, and the natural verbalization of symbolic special expressions. In this paper, we introduce S$^3$-Bench, a systematic evaluation framework covering 10 major disciplines, consisting of a Knowledge set for speech question-answering and a Dialogue set for multi-turn progressive interactions with simulated user agents. By decomposing a complete atomic turn into stages of speech recognition, perception, knowledge utilization with reasoning, and response pronunciation, we systematically characterize the common challenges and performance tradeoffs of existing approaches. Furthermore, experiments on multi-turn interactions reveal persistent limitations in user adaptation and the generation of accurate, comprehensive, and efficient responses.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09852
PDF
-
StreamAlign: Streaming Text-Aligned Speech Tokenization
2026-09-09 05:03:12Kang-wook Kim, Jinyoung Park, Jinsoo Kim, Sehun Lee, Sang Hoon Woo, Gunhee KimAbstract
Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretrained LLMs. However, they rely on offline automatic speech recognition (ASR), leading to two key limitations: (i) the need for complete utterances before tokenization, precluding real-time streaming, and (ii) vocabulary mismatch between ASR and LLMs, which reduces acoustic granularity from the subword to the word level. We introduce StreamAlign, a text-aligned speech tokenization framework that enables streaming tokenization for real-time speech-text joint modeling. StreamAlign performs online speech-text alignment by combining character-level RNN-Transducer alignment with word-level ASR guidance, mitigating ASR-LLM vocabulary mismatch while preserving recognition accuracy. A proactive word boundary classifier anticipates word completion at chunk boundaries, reducing tokenization latency from 560 ms to 270 ms. On LibriSpeech, StreamAlign achieves the lowest WER and highest UTMOS among evaluated tokenizers. Furthermore, StreamAlign-SLM, a spoken language model trained on StreamAlign units, outperforms other end-to-end spoken language models in speech continuation while achieving the strongest overall consistency on SALMon and spoken StoryCloze.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09719
PDF
-
SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia
2026-09-09 03:39:18Jingyi Liao, Wenyu Zhang, Zhuohan Liu, Yingxu He, Geyu Lin, Xunlong Zou, Shuo Sun, Syed Ali Redha Alsagoff, Ai Ti AwAbstract
The rapid advancement of audio and multimodal large language models has unlocked transformative speech understanding capabilities, yet evaluation frameworks remain predominantly English-centric, leaving Southeast Asian (SEA) languages critically underrepresented. We introduce SEA-SpeechBench, to the best of our knowledge, the first large-scale multitask benchmark that evaluates speech understanding in 11 SEA languages through 97,194 samples across 99 evaluation sets and 597 hours of curated audio data. Our benchmark comprises 9 diverse tasks across 3 categories: speech processing (automatic speech recognition, speech translation, spoken question answering), paralinguistic analysis (emotion, gender, age, speaker recognition), and temporal understanding, a novel dimension featuring timestamped content queries and temporal localization within extended audio sequences up to 3 minutes. We implement multilingual prompting in both native SEA languages and English to reflect user interactions with audio-language models. Evaluation of leading open-source and proprietary systems reveals marked performance gaps. Across all models, performance remains underwhelming on temporal understanding, emotion recognition, and speech translation. Prompting in low-resource languages such as Burmese and Tamil lags behind English by up to 41 percentage points. Our findings expose critical model limitations and underscore the need for inclusive model development. The SEA-SpeechBench benchmark is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09672
PDF
-
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models
2026-09-09 00:18:08Shivam Singh, Aditya Yadavalli, Catherine Arnett, Alex WarstadtAbstract
We introduce BuzzASR, a collection of language-specialized fine-tuned Whisper models adapted for automatic speech recognition (ASR) in 102 languages. Large end-to-end Transformer-based ASR models such as Whisper have revolutionized ASR, but most prominent models are highly multilingual. As a result, these models often perform poorly on languages less well-represented in their training set. While it has long been known that effective language adaptation can be achieved through simple fine-tuning on monolingual data, this strategy has only been applied to a small number of languages. We massively scale up this simple approach to 102 languages covered in the FLEURS dataset, while also implementing a more complex language adaptation strategy that integrates monolingual tokenizer replacement and data augmentation using text-only fine-tuning. BuzzASR models outperform Whisper-large-v3 on 77 out of 102 languages, reducing character error rates (CER) by a factor of over 2.8 on average. Our models achieve state-of-the-art CER among open-source systems on 27 of 102 languages on the combined FLEURS and Common Voice test set. Our tokenizer replacement strategy yields an average 3.3x improvement in compression rate (characters per token) over Whisper's multilingual BPE, with gains of up to 21.7x. We release all models, code, and detailed results: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.09554
PDF
-
X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR
2026-09-08 12:39:06Zhiwei Lin, Kaiqi Fu, Rime Wen, Zehan Liu, Shawn Qin, Roy Gan, Hao Wang, Qian WangAbstract
Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low commit latency. Existing systems commonly use a fixed chunk size, look-ahead, or target delay, or encourage emissions near estimated acoustic boundaries. These approaches do not directly optimize how much additional context to use at each output position under a single-pass, hard-commit constraint. We propose X2Streaming-ASR, which decomposes streaming recognition into when to commit and what to commit. Its three-stage training procedure first establishes streaming recognition ability, then warm-starts the commit policy with automatically probed trajectories, and finally refines the policy using character-level, segment-assigned group-relative rewards for recognition accuracy and latency. Across AISHELL-1/2/3 and WenetSpeech, X2Streaming-ASR achieves a mean character-level commit latency of 27-84 ms relative to forced-aligned character endpoints, compared with 409-585 ms for the evaluated streaming baselines. It achieves the best streaming CER among the evaluated systems on AISHELL-1 and AISHELL-3 with substantially lower latency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08672
PDF
-
Development of a Humanoid Robot Prototype for Multimodal Human-Robot Interaction
2026-09-04 17:06:47Thang Tran Viet, Thanh Nguyen Canh, Huy Uong Gia, Phuc Dinh Van, Son Tran Duc, Ngoc Minh Do, Xiem HoangVanAbstract
Human-robot interaction (HRI) enables intuitive and intelligent collaboration between humans and robots in real-world environments. This paper introduces a humanoid robot prototype designed as a flexible testbed for developing and integrating artificial intelligence (AI) modules in HRI tasks. The system features a 12 degree-of-freedom (DOFs) dual-arm mechanism and a 2 DOFs head with an expressive LCD screen to express facial emotions. All hardware components are controlled by a custom-designed controller board with real-time AI processing supported by an onboard Jetson module. The system incorporates three AI modules: (1) gesture recognition using MediaPipe Pose and an LSTM classifier, (2) object detection with YOLO and 3D localization, and (3) voice-command processing through speech recognition and large language model(LLM)-based semantic parsing. The platform is validated through experiments on positioning accuracy, with results showing average manipulation errors of approximately 1.83 cm. To demonstrate its versatility, experimental results show over 90% task accuracy, with gesture recognition reaching 96%, speech recognition reaching 92%. The results confirm the effectiveness of the proposed system as a reproducible and accessible humanoid platform for research and prototyping in HRI.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05361
PDF
-
Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection
2026-09-03 23:33:12Maryam Abbasihafshejani, Murtuza JadliwalaAbstract
Whisper is a widely used foundation model for automatic speech recognition (ASR), but its generative decoder can produce fluent hallucinated transcripts for inputs containing little or no speech. We propose a training-free, inference-time method to reduce these hallucinations using low-rank projection of decoder activations. A compact hallucination-associated subspace is estimated from non-speech calibration data, and decoder hidden states are projected away from this subspace during inference. We evaluate two variants: always-on, which applies projection to all inputs, and gated, which applies it only when Whisper predicts that an input is likely non-speech. Across non-speech benchmarks, always-on projection reduces average hallucination rate (HR) from 31.31% to 2.44%, a 92.21% relative reduction, while gated projection reduces HR to 3.74%, an 88.05% relative reduction, with lower false rejection of genuine speech. On LibriSpeech, gated projection increases absolute word error rate (WER) by 0.33-4.39 percentage points and yields false-rejection rates (FRR) of 0.41--9.97% across model and split settings. These results show that low-rank activation projection can substantially suppress Whisper hallucinations without retraining, while providing a controllable trade-off between hallucination suppression and speech recognition performance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04561
PDF
-
TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio
2026-09-03 20:14:48Chaewan Chun, Meruyert Aristombayeva, Jiyoung Choi, Mahjabin Nahar, Delvin Ce Zhang, Dongwon LeeAbstract
Modern misinformation is often heard before it is read, yet fact-checking systems are still evaluated mainly on clean written claims. Spoken dialogue remains different even when systems operate on transcripts: claims may be distributed across speakers and turns, depend on prior context, and become harder to verify when Automatic Speech Recognition (ASR) errors distort the available text. Prior spoken dialogue fact-checking resources are small, English-centric, or focused on annotation rather than end-to-end benchmarking, leaving no large multilingual benchmark with paired speech and turn-level labels. We introduce TRILOGUE (TRIlingual spoken diaLOGUE fact-checking), a large-scale trilingual benchmark of source-grounded spoken dialogues in English, Russian, and Kazakh. It contains nearly 12K dialogues, 187K turns, and 390 hours of paired audio with ASR transcripts and word-level timestamp alignments across all three languages, including nearly 5K human-recorded Russian and Kazakh dialogue files. TRILOGUE supports claim check-worthiness detection, source-article evidence retrieval, and claim verification with claim-only, gold-evidence, and retrieved-evidence inputs. Baselines show that ASR degradation and cross-lingual transfer remain challenging, especially for Kazakh, while retrieved source evidence substantially narrows the gap to gold-evidence verification.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04452
PDF
-
Choosing a PEFT Variant for Per-Patient Dysarthric ASR: A Single-Speaker Case Study on Two ASR Bases
2026-09-02 15:42:48Bernard Muller, L\'aszl\'o T\'oth, LaVonne RobertsAbstract
Per-patient adapters are the preferred production architecture for dysarthric automatic speech recognition (ASR), yet parameter-efficient fine-tuning (PEFT) variants have not been compared in the speaker-dependent, per-patient regime. We present a single-speaker case study comparing seven LoRA-family methods (LoRA, QLoRA, AdaLoRA, DoRA, LoHA, VeRA, VB-LoRA) on two production bases (Whisper-large-v3 with Hungarian fine-tuning, and a multilingual Qwen3-ASR-1.7B checkpoint) for one post-stroke Hungarian male speaker (S1, 409 utterances; severe dysarthria on auditory-perceptual clinical assessment). Attention-projection adapters substantially improve CER on both bases. Across three seeds, a paired bootstrap detects no significant LoRA-DoRA difference (p>0.5; 13.86/13.90 % CER on Whisper, 28.10/28.33 % on Qwen3-ASR), so we adopt the simpler, cheaper LoRA. Real 4-bit (NF4) QLoRA is worse on every seed and both bases (14.56/30.09 % CER) with no memory saving at this scale, and LoHA, VeRA, VB-LoRA and AdaLoRA do not reach the LoRA family, though LoHA still gives an 18.6 % relative CER reduction on Whisper. On the same base, full fine-tuning is more accurate (11.43 % CER), but a 115 MB LoRA that also adapts the feed-forward blocks reaches within 0.66 pp of it at approximately 3.7 % of the per-patient storage. A 6-point enrollment grid shows about 5 min of patient audio captures 45.6 % of the zero-shot-to-30-min CER reduction, with further gains at 10 and 30 min (caveat: one speaker, one language, severe post-stroke dysarthria). Training scripts and recipes will be released, source-available under a research-use licence, on publication.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02735
PDF
-
GhostWord: A Fine-Grained Backdoor Attack on Automatic Speech Recognition
2026-09-02 09:32:39Mojtaba Nafez, Mobina Poulaei, Kiarash Kiani Feriz, Aref Mousavi, Mohammad Ebrahim Mahdavi, Mohammad Mosayebi, Mohammad Hossein RohbanAbstract
Automatic Speech Recognition (ASR) systems are widely deployed in safety-critical settings but remain vulnerable to data-poisoning backdoor attacks. Existing ASR backdoors typically use phrase-level triggers paired with a fixed target sentence, creating strong artifacts (e.g., repeated transcripts or triggers placed in non-speech regions) that simple preprocessing can mitigate. We propose GhostWord, a word-level, time-localized ASR backdoor that uses codebooks mapping short ($\approx$400\,ms) acoustic triggers to target words. During poisoning, we inject a trigger into the forced-aligned time span of a chosen source word in the audio and replace only that word in the transcript, enabling precise semantic flips and composable sentence manipulation while avoiding many-to-one label artifacts. Across Common Voice (v23 English, v24 Lithuanian) and multiple backbones (Whisper-Small/Medium, MMS, SpeechT5), GhostWord achieves an average attack success rate of 89.3\% and transfers across languages and models. Adapting optimization-based defenses (ABL, ANP, SAU, I-BAU) reveals a sharp robustness--accuracy trade-off: attack success drops from 89.3\% to 29.1\% while clean WER rises from 21.5\% to 45.0\%, consistent with our theoretical analysis showing that, in high-vocabulary models, backdoor suppression structurally tends to degrade clean performance. The source code is publicly available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.04260
PDF
-
SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition
2026-09-01 18:07:24Biraj SubediAbstract
Mobile payment applications in Nepal are graphically mediated and largely inaccessible to visually impaired users. This paper presents SpeakPay, a voice-first digital wallet, and documents the central technical contribution: a controlled study of domain adaptation for low-resource financial speech recognition. We introduce NepFinSpeech-403, a 403-utterance dataset of Nepali financial voice commands (send, load, and balance operations spanning 237 unique numerals), and fine-tune Whisper large-v2 with LoRA. On the held-out test set, the domain-adapted model reduces Word Error Rate from 129.95% (zero-shot baseline) to 42.58% --- a 67.2% relative reduction --- and improves Devanagari numeral recognition accuracy from 0.0% to 73.9%. We find that word-level metrics understate the practical task-level impact: domain adaptation improves the Transaction Success Rate from 1.67% to 33.33%, a roughly 20x gain. The improvement is consistent at the individual-utterance level (sign test, $p < 10^{-17}$) and across all command types. A data efficiency analysis shows that as few as 100 domain-specific utterances are sufficient to halve the zero-shot WER, with performance plateauing around 300 examples. Error analysis reveals systematic numeral confusion patterns (zero insertion/deletion, prefix hallucination) that account for the majority of remaining transaction failures. The trained system is deployed as a publicly accessible voice-first web application. All code, dataset, model weights, and this paper are released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01737
PDF
-
Soft Posterior Speaker Injection for Multi-Talker Speech Recognition
2026-09-01 14:23:27Jian Zhu, Cheng LuoAbstract
Multi-talker automatic speech recognition (MT-ASR) remains challenging under overlapping speech. Hard diarization-based segmentation introduces irreversible errors, whereas serialized output training (SOT) avoids explicit segmentation but does not condition a pretrained encoder on speaker activity. We propose Soft Posterior Speaker Injection (SPSI): a lightweight head predicts frame-level speaker posteriors $\hat{\mathbf{P}}$ and injects them into Whisper through multi-layer feature-wise linear modulation (FiLM) and decoder speaker-memory prompts. On controlled two-speaker LibriSpeech overlap, SPSI reduces utterance-mean constrained permutation word error rate (cpWER) from 50.7\% (SOT) to 49.6\% (one-sided paired bootstrap $p{\approx}0.006$), with a larger reduction in the high-overlap bin (60.4\%$\to$58.8\%). Same-backbone speaker-auxiliary objectives and voice activity detection (VAD) pipelines do not outperform SOT; zero-shot (ZS) LibriCSS is comparable. Freeze-posterior adaptation with overlap-heavy (OV-heavy) continuation reduces held-out LibriCSS cpWER (sessions 8--9) to 32.4\% (versus 37.5\% for SOT). Ablations indicate complementary encoder FiLM and decoder prompts, and that the effective signal is a \emph{soft} simplex-valued speaker share.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01287
PDF
-
Human-robot conversation with multiple participants in noisy public spaces
2026-09-01 03:25:03Divesh Lala, Yogeeswaran Muthukumaran, Vincent Fernandes, Kazushi Kato, Shota Fujiki, Zihao Chi, Masaya Iwasaki, Taiken Shintani, Megumi Kawata, Kazuki Sakai, Koji Inoue, Yuicihiro Yoshikawa, Tatsuya KawaharaAbstract
For noisy real-world environments such as those in open public spaces, spoken dialogue systems for both autonomous robots and avatars should be carefully designed to provide enhanced speech signals. These signals can be used either for speech recognition or, in the case of an avatar system, transmitted as clean speech to a remote operator. This work proposes an audio system that can be used for both these scenarios and was demonstrated as a proof-of-concept at the 2025 World Expo in Osaka. The first scenario is an attentive listening system with the android ERICA, and the second is a conversation support system with mobile Teleco robots, with one of them acting as an avatar for a remote operator. Both systems feature multi-party conversation and use a single multi-channel microphone array. We describe how our audio system not only enhances the speech of multiple speakers in a noisy environment, but provides a form of spatial audio which allows for more immersiveness in avatar-based conversational interactions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00648
PDF
-
Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversations
2026-08-31 22:26:50Fanyou Wu, Suraj Maharjan, Ainur Yessenalina, Dennis Xu Chen, Rahul Srivastava, Srinivasan H. SengameduAbstract
Effective manager-employee communication is critical for retaining high performers and developing underperformers, yet training managers in these skills remains costly. Text-based chatbots offer a scalable approach but cannot provide realistic rehearsal: managers need to practice speaking aloud to build confidence before high-stakes conversations. In this paper, we propose Conversation Coach, a voice-first AI system that enables managers to rehearse difficult workplace conversations in a realistic spoken format. The system addresses three challenges: achieving low-latency interactions with strong language understanding, enabling adaptive conversations through configurable bot personalities that simulate different employee types, and generating personalized feedback on content and policy compliance. We compare an end-to-end speech-to-speech model with a cascaded approach combining automatic speech recognition, a large language model, and text-to-speech synthesis. The end-to-end approach achieves 3$\times$ lower median (P50) latency with native barge-in capability at an estimated 8$\times$ lower cost, while the cascaded approach offers superior reasoning essential for coaching quality. We deployed the cascaded architecture in production, where 40,000+ managers used it over six months, with adoption patterns indicating selective use for difficult conversations.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00441
PDF
-
Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models
2026-08-31 18:11:36Linhai Ma, Rita El Hachem, Mahatab El Hajj, Lilian Ghandour, Samah FodehAbstract
Crisis helplines assess suicide risk through structured interviews, a process that is slow and dependent on operator training and workload. Natural language processing could support risk assessment and call prioritization, but almost no work addresses Arabic-language helpline calls or operates within the privacy constraints of real helpline data. We analysed de-identified transcripts from Lebanon's National Lifeline for Emotional Support and Suicide Prevention. Audio never left the helpline: calls were transcribed on site with a speech recognition model for Levantine Arabic, and an Arabic named-entity recognition model removed identifying information locally. Only the de-identified transcripts were shared with the research team. Operators recorded the five suicidal ideation items of the Columbia Suicide Severity Rating Scale, which we combined into two binary outcomes: at-risk and high-risk. We also machine-translated the transcripts into English, giving a paired Arabic/English comparison. On each corpus, we fine-tuned five instruction-tuned large language models alongside six transformer encoder baselines (four Arabic, two English) and evaluated all models on a held-out test set. We included 383 calls: 373 for the at-risk task (52.3% positive) and 297 for the high-risk task (30.0% positive). The best Arabic model reached a macro-F1 of 81.19 and a ROC-AUC of 90.61 on high-risk; the best English model reached 85.00 and 92.59, identifying 88.9% of high-risk calls. In both languages, high-risk calls separated more cleanly than at-risk calls, and translation to English did not reduce the best observed performance. Suicide risk can be classified from de-identified Arabic transcripts without sending audio outside the helpline. The high-risk results support further testing as an operator-facing tool; lower-severity ideation proved the harder case.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00191
PDF
-
Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions
2026-08-31 15:46:48Chan-Jan Hsu, Jaeyeon Kim, Chao-Han Huck Yang, Shinji Watanabe, Hung-yi Lee, Carlos BussoAbstract
Recent automatic speech recognition (ASR) systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge, either externally through logit fusion or internally through warm initialization. However, how to effectively combine these two strategies remains underexplored. In this work, we refine warm-initialized LLM-based ASR models by leveraging their own pre-adaptation base LLMs, focusing on LoRA-adapted settings where the base LLM is preserved. To achieve this, we propose Hybrid Search, a targeted correction strategy motivated by two observations. First, interaction features that characterize the relationship between LLM-based ASR hidden states and base-LLM hidden states provide informative signals about a token's degree of semantic dependence. Second, selectively refining targeted tokens with high semantic dependence improves ASR performance far beyond naive global LLM-correction methods including rescoring and late fusion. Our analysis suggests that, even after semantic knowledge transfer through warm initialization, LLM-based ASR models can still leverage their base LLM to further improve inference-time performance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02940
PDF
