# Qwen-Audio-3.0-ASR Technical Report

arXiv: https://arxiv.org/abs/2609.07549 · HTML: https://mlsanity.com/paper/2609.07549/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 23 of its 25 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs](https://mlsanity.com/paper/2407.04051/) (2024)
- [Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition](https://mlsanity.com/paper/2407.04675/) (2024)
- [Fun-ASR Technical Report](https://mlsanity.com/paper/2509.12508/) (2025)
- [Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition](https://mlsanity.com/paper/2603.11123/) (2026)
- [Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition](https://mlsanity.com/paper/2409.17746/) (2024)
- [Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning](https://mlsanity.com/paper/2512.21828/) (2025)
- [Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Study](https://mlsanity.com/paper/2409.17750/) (2024)
- [Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling](https://mlsanity.com/paper/2606.10439/) (2026)
- [GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark](https://mlsanity.com/paper/2606.28884/) (2026)
- [FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation](https://mlsanity.com/paper/2608.24168/) (2026)
- [Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction](https://mlsanity.com/paper/2604.12398/) (2026)
- [MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond](https://mlsanity.com/paper/2607.22100/) (2026)

## Built on by (most cited first, 2 of 2)

- [Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction](https://mlsanity.com/paper/2609.25176/) (2026)
- [ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context](https://mlsanity.com/paper/2610.16260/) (2026)

## Abstract (arXiv)

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.