mlsanityData to 14 Oct 2026

Qwen3-ASR Technical Report

arXiv 2601.21337 ↗First posted 29 Jan 2026cs.CL cs.SD eess.AScited by 118

Not on the map. Why?

Abstract (arXiv)

In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support language identification and ASR for 52 languages and dialects. Both of them leverage large-scale speech training data and the strong audio understanding ability of their foundation model Qwen3-Omni. We conduct comprehensive internal evaluation besides the open-sourced benchmarks as ASR models might differ little on open-sourced benchmark scores but exhibit significant quality differences in real-world scenarios. The experiments reveal that the 1.7B version achieves SOTA performance among open-sourced ASR models and is competitive with the strongest proprietary APIs while the 0.6B version offers the best accuracy-efficiency trade-off. Qwen3-ASR-0.6B can achieve an average TTFT as low as 92ms and transcribe 2000 seconds speech in 1 second at a concurrency of 128. Qwen3-ForcedAligner-0.6B is an LLM based NAR timestamp predictor that is able to align text-speech pairs in 11 languages. Timestamp accuracy experiments show that the proposed model outperforms the three strongest force alignment models and takes more advantages in efficiency and versatility. To further accelerate the community research of ASR and audio understanding, we release these models under the Apache 2.0 license.

Key facts. Cited by 118 papers in the map (data through 14 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

12 of 23 references.

References · 12

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  3. 2015Listen, Attend and Spellcited by 543
  4. 2025Qwen3-Omni Technical Reportcited by 497
  5. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  6. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 197
  7. 2020CTC-Segmentation of Large Corpora for German End-to-end Speech Recognitioncited by 76
  8. 2023Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Modelcited by 10
  9. 2025Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methodscited by 10
  10. 2025WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotationcited by 9
  11. 2026LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speechcited by 9
  12. 2025WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processingcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 118.

118 papers.

Sort:

By area:

  1. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  2. 2026GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Taskscited by 14
  3. 2026MOSS-Audio Technical Reportcited by 11
  4. 2026PASK: Toward Intent-Aware Proactive Agents with Long-Term Memorycited by 9
  5. 2026Raon-Speech Technical Reportcited by 7
  6. 2026Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognitioncited by 6
  7. 2026Dynin-Omni: Omnimodal Unified Large Diffusion Language Modelcited by 5
  8. 2026Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulationcited by 5
  9. 2026Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarizationcited by 4
  10. 2026Audio Interaction Modelcited by 4
  11. 2026Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decodingcited by 3
  12. 2026ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Modelscited by 3
38 more
  1. 2026X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Predictioncited by 3
  2. 2026Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modelingcited by 2
  3. 2026Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluationcited by 2
  4. 2026MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answeringcited by 2
  5. 2026VoiceMem: Streaming Dual-Brain Memory for Real-Time Interactioncited by 2
  6. 2026Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASRcited by 1
  7. 2026TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wildcited by 1
  8. 2026Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessmentcited by 1
  9. 2026Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMscited by 1
  10. 2026Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognitioncited by 1
  11. 2026NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASRcited by 1
  12. 20262nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VAcited by 1
  13. 2026Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understandingcited by 1
  14. 2026When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognitioncited by 1
  15. 2026Dolphin-CN-Dialect: Where Chinese Dialects Mattercited by 1
  16. 2026FormalASR: End-to-End Spoken Chinese to Formal Textcited by 1
  17. 2026LaSR: Context-Aware Speech Recognition via Latent Reasoningcited by 1
  18. 2026FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognitioncited by 1
  19. 2026Bagpiper-TTS: Natural Language Guided Universal Speech Synthesiscited by 1
  20. 2026Adapting Foundation ASR Models to Dysarthric Speech: A Case Studycited by 1
  21. 2026InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generationcited by 1
  22. 2026AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approachcited by 1
  23. 2026Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASRcited by 1
  24. 2026How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMscited by 1
  25. 2026AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editingcited by 1
  26. 2026DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Eventscited by 1
  27. 2026Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Modelscited by 1
  28. 2026Omni2Web: Benchmarking Audiovisual Website Developmentcited by 1
  29. 2026Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challengecited by 1
  30. 2026AST: Adaptive, Seamless, and Training-Free Precise Speech Editingcited by 0
  31. 2026Tadabur: A Large-Scale Quran Audio Datasetcited by 0
  32. 2026AppTek Call-Center Dialogues: A Multi-Accent Long-Form Benchmark for English ASRcited by 0
  33. 2026VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Modelscited by 0
  34. 2026EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillationcited by 0
  35. 2026PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesiscited by 0
  36. 2026MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priorscited by 0
  37. 2026Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancycited by 0
  38. 2026Vibrato Expression Control for Singing Voice Conversion with Improving Independent Controlcited by 0

50 most cited of 118 All 118 (JSON)