Streaming ASR

ASR: Automatic Speech Recognition

Ask about this topic

Overview

Streaming ASR studies how to turn incoming audio into text before the speaker has finished, which matters for live captions, voice agents, and on-device interfaces. Common approaches include RNN-T and CTC transducers, chunk-wise attention, and cache-aware encoders that limit how much future audio the model must wait for. Newer systems also use language-model context, adaptive commit policies, and distillation or quantization to improve recognition and run on constrained hardware. The central challenge is balancing transcription accuracy against emission delay, memory, and power, especially across languages, noisy speech, and conversational turn boundaries.

Latest papers

CardsList

39 papers7 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. RoleHear: Pseudo-Labeling for Semi-Supervised Role-Attributed Streaming Speech Recognition

    Oct 24, 2026Zefang Liu, Chenyang Zhu, Sangwoo Cho +4Speaker-Attributed ASRAutomatic Speech Recognition

    Capital One, USA

  2. Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and Recognition

    Oct 23, 2026Xuan Shi, Chang Zeng, Tiantian Feng +5Speech ProcessingSpeech Language Models

    University of Southern California, USA · National Institute of Informatics, Japan · Massachusetts Institute of Technology, USA +1

  3. Qwen-Audio-3.1-ASR Technical Report

    Oct 20, 2026Chuanmeng Bian, Daren Chen, Peixin Chen +45Audio-Language ModelsAutomatic Speech Recognition

  4. Ask, Don't Guess: Targeted Clarification for Speech Recognition Errors

    Oct 17, 2026Sankalp Parashar, Preethi Jyothi, Sunita SarawagiAutomatic Speech RecognitionStreaming ASR

    IIT Bombay

  5. Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation

    Oct 16, 2026Mahmoud AshrafMemory-Efficient TrainingStreaming ASR

    Tarteel AI

  6. Oído: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator

    Oct 9, 2026Daniel Varela Sánchez, Guillermo Martín-Coello JuárezAutomatic Speech RecognitionStreaming ASR

    Lokutor (Hashing Works, S.L.L.), Madrid, Spain

  7. Factorized Delayed Streams Modeling for LLM-based Streaming ASR

    Oct 3, 2026Tatsunari Takagi, Kai Washizaki, Atsushi Kojima +3Streaming ASRSpeech Language Models

    SB Intuitions · Toyohashi University of Technology

  8. Multi-Teacher Distillation for Cross-Domain Streaming Electrolaryngeal Speech Encoding

    Sep 16, 2026Benedikt Mayrhofer, Enrique Orozco Olivares, Franz Pernkopf +2Audio Representation LearningStreaming ASR

    Signal Processing and Speech Communication Laboratory, Graz University of Technology · Comprehensive Center for AI in Medicine, Medical University of Vienna · Dept. of Otolaryngology, Head & Neck Surgery, Div. of Phoniatrics-Logopedics, Speech & Hearing Sci. Lab, Med. Univ. of Vienna

  9. Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR

    Sep 16, 2026Xiuwen ZhengStreaming ASRSpeech Language Models

    University of Illinois Urbana-Champaign

  10. Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models

    Sep 14, 2026Ke Hu, Nourchene Ferchichi, Edresson Casanova +9Streaming ASRSpeech Processing

    NVIDIA

  11. Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

    Sep 14, 2026Warit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani +2Streaming ASRAutomatic Speech Recognition

    Typhoon Team, SCB DataX, Bangkok, Thailand

  12. Pushing the Boundaries of Streaming Multi-Speaker ASR: A Systematic Study of Architectural Trade-offs

    Sep 9, 2026Taejin Park, Ivan Medennikov, Kunal Dhawan +3Multi-Speaker ASRStreaming ASR

    NVIDIA, Santa Clara, CA, United States

  13. X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR

    Sep 8, 2026Zhiwei Lin, Kaiqi Fu, Rime Wen +4Streaming ASRAutomatic Speech Recognition

    X Square Robot

  14. Qwen-Audio-3.0-ASR Technical Report

    Sep 7, 2026Chuanmeng Bian, Daren Chen, Peixin Chen +42Contextual ASRStreaming ASR

  15. VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition

    Aug 28, 2026Tyler Baumgartner, Brandon Tai, Lisa Kaelin-Martin +4Speech Recognition BenchmarksAutomatic Speech Recognition

    Besimple AI, San Mateo, CA, USA

  16. Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents

    Aug 22, 2026Sameep Chattopadhyay, Alexander Erdmann, Mari OstendorfConversational Speech RecognitionStreaming ASR

    University of Washington · SRI International

  17. TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems

    Aug 21, 2026Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko +3Contextual ASRAutomatic Speech Recognition

    NVIDIA, Yerevan, Armenia · NVIDIA, Santa Clara, USA

  18. StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition

    Aug 13, 2026Zefang Liu, Chenyang Zhu, Sangwoo Cho +3Automatic Speech RecognitionStreaming ASR

    Capital One, USA

  19. X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction

    Aug 11, 2026Kaiqi Fu, Rime Wen, Altman Lin +4Streaming ASRMulti-Task Learning

    X Square Robot

  20. AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach

    Jul 30, 2026Zixuan Jiang, Binghao Qiang, Jiaying Chi +3ASR EvaluationStreaming ASR

    X-LANCE lab, Shanghai Jiao Tong University · Shanghai Innovation Institute · College of Artificial Intelligence, Xi’an Jiaotong University

  21. Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding

    Jul 24, 2026Pengfei Zhang, Biao Tian, Tianxin Xie +3Speaker-Attributed ASRContextual ASR

    AI Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou) · Token Foundry, Alibaba Group, China

  22. From a Multilingual Streaming ASR Backbone to Kenyan-Language Systems: Data-Centric Adaptation of Nemotron 3.5 for Kikuyu, Dholuo, and Kalenjin

    Jul 21, 2026Mark GatereFine-TuningStreaming ASR

    C-elo Labs

  23. NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs

    Jul 1, 2026Sihyeon Lee, Hojeong Lee, Sungwon Woo +3Efficient Transformer InferenceStreaming ASR

    Korea University · University of Wisconsin–Madison

  24. Data Scale, Not Latency, Shapes Cross-Lingual Encoder Transfer in Streaming ASR

    Jun 23, 2026Nenad BanficStreaming ASRLow-Resource Speech Recognition

    CoreAI, Microsoft

  25. Online Predictive Coding for Dual-Mode Self-Supervised Speech Model

    Jun 19, 2026Keita Goto, Takashi Maekaku, Jin Sakuma +3Predictive CodingStreaming ASR

    LY Corporation, Tokyo, Japan · Carnegie Mellon University, PA, USA

  26. Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction

    Jun 16, 2026Tristan Tsoi, Jiajun Deng, Yingke Zhu +5Event Time PredictionStreaming ASR

    Central Media Technology Institute, Huawei · The Chinese University of Hong Kong · Nanyang Technological University

  27. TRADE: Transducer-Augmented Decoder for Speech LLM

    Jun 7, 2026Yun Tang, Shanil Puri, Shinji Watanabe +1Streaming ASRSpeech Processing

    Hippocratic AI · Carnegie Mellon University

  28. Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

    Jun 5, 2026Jiani Xie, Andrew C. Cullen, Paul Montague +1Streaming ASRAutomatic Speech Recognition

    University of Melbourne · DST Group

  29. Symphony for Speech-to-Text: Supporting Real-Time Medical Voice Interfaces

    May 15, 2026Arne Nix, Robert James, Lasse Borgholt +6HealthcareStreaming ASR

    Corti

  30. Dolphin-CN-Dialect: Where Chinese Dialects Matter

    May 9, 2026Yangyang Meng, Huihang Zhong, Guodong Lin +6Streaming ASRAutomatic Speech Recognition

    1Dataocean AI · 2Speech and Audio Technology Lab, Dept. EE, Tsinghua University