Qwen-Audio-3.0-ASR Technical Report

• URL: http://arxiv.org/abs/2609.07549v2
• Date: Wed, 09 Sep 2026 11:59:55 GMT
• Title: Qwen-Audio-3.0-ASR Technical Report
• Abstract summary: We present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system.<n>Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions.<n>We develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications.
• Score: 52.28849889799101
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Qwen3.5-Omni Technical Report [0.0]
  Qwen3.5- Omni scales to hundreds of billions of parameters and supports a 256k context length.<n>Qwen3.5- Omni results across 215 audio and audio-visual understanding, reasoning, and interaction subtasks and benchmarks.<n>ARIA dynamically aligns text and speech units, significantly enhancing the stability and prosody of conversational speech.
  arXiv  Detail & Related papers  (2026-04-17T08:05:46Z)
• PRiSM: Benchmarking Phone Realization in Speech Models [70.82595415252682]
  Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis.<n>We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception.
  arXiv  Detail & Related papers  (2026-01-20T15:00:36Z)
• AHELM: A Holistic Evaluation of Audio-Language Models [78.20477815156484]
  multimodal audio-language models (ALMs) take interleaved audio and text as input and output text.<n>AHELM is a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE and CoRe-Bench.<n>We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models.
  arXiv  Detail & Related papers  (2025-08-29T07:40:39Z)
• Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction [110.38946048535033]
  This paper introduces Step-Audio, the first production-ready open-source solution for speech recognition.<n>Key contributions include: 1) a unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex
  arXiv  Detail & Related papers  (2025-02-17T15:58:56Z)
• Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition [110.8431434620642]
  We introduce the generative speech transcription error correction (GenSEC) challenge. This challenge comprises three post-ASR language modeling tasks: (i) post-ASR transcription correction, (ii) speaker tagging, and (iii) emotion recognition. We discuss insights from baseline evaluations, as well as lessons learned for designing future evaluations.
  arXiv  Detail & Related papers  (2024-09-15T16:32:49Z)
• Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong's Polylingual Dynamics [0.5700195008916903]
  We develop a 34.8-hour dataset of Mixed Cantonese and English (MCE) audio using our Multi-Agent Data Generation Framework (MADGF)<n>We fine-tuned the open-source multilingual Automatic Speech Recognition (ASR) model, Whisper, with the MCE dataset, leading to impressive zero-shot performance.
  arXiv  Detail & Related papers  (2023-10-27T08:01:55Z)
• Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech [6.243356997302935]
  We introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations from recordings in the target language, which are then used to train a single-speaker acoustic model.
  arXiv  Detail & Related papers  (2023-09-15T09:03:14Z)
• How Phonotactics Affect Multilingual and Zero-shot ASR Performance [74.70048598292583]
  A Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. We replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer.
  arXiv  Detail & Related papers  (2020-10-22T23:07:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.