Qwen-Audio-3.1-ASR Technical Report

Hugging Face Daily Papers Papers
audio-understanding automatic-speech-recognition speaker-diarization multilingual audio-language-model qwen

Summary

Qwen-Audio-3.1-ASR 技术报告介绍了一系列音频语言模型，在语音识别、说话人分离转录和通用音频理解方面较 Qwen-Audio-3.0-ASR 有显著提升，支持 30 种语言和 16 种汉语方言，并提供流式与非流式等多种部署变体。

We present Qwen-Audio-3.1-ASR, a family of audio-language models that builds upon its predecesor Qwen-Audio-3.0-ASR with improved speech recognition and expanded capabilities in speaker-diarized transcription and general audio understanding. The family retains support for 30 languages and 16 Chinese dialects, together with instruction-controlled capabilities including historical-context conditioning, hierarchical hotword customization, and native transcription polishing. Speaker-diarized ASR produces structured outputs containing speaker labels, timestamps, and recognized text, maintaining consistent speaker labels across turns and the representation of overlapping speech. The general audio understanding capabilities cover audio-, speech-, and music-captioning, temporal grounding and sound event detection, as well as audio question answering and multiple-choice reasoning. These tasks broaden the application scope from recognizing spoken words to interpreting speakers, acoustic events, and their temporal relations. To accommodate different deployment requirements, the family includes variants for asynchronous file transcription, low-latency streaming, interactive voice input, and non-streaming recognition, with speaker-diarized transcription and general audio understanding available in certain variants. Evaluations span conventional ASR, multilingual and dialectal speech, speaker-diarized transcription, and general audio understanding, demonstrating the capabilities of the Qwen-Audio-3.1-ASR family across transcription and broader audio analysis tasks.
Original Article
View Cached Full Text

Cached at: 10/22/26, 03:41 PM

Paper page - Qwen-Audio-3.1-ASR Technical Report

Source: https://huggingface.co/papers/2610.28711 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

WepresentQwen-Audio-3.1-ASR,afamilyofaudio-languagemodelsthatbuildsuponitspredecesorQwen-Audio-3.0-ASRwithimprovedspeechrecognitionandexpandedcapabilitiesinspeaker-diarizedtranscriptionandgeneralaudiounderstanding.Thefamilyretainssupportfor30languagesand16Chinesedialects,togetherwithinstruction-controlledcapabilitiesincludinghistorical-contextconditioning,hierarchicalhotwordcustomization,andnativetranscriptionpolishing.Speaker-diarizedASRproducesstructuredoutputscontainingspeakerlabels,timestamps,andrecognizedtext,maintainingconsistentspeakerlabelsacrossturnsandtherepresentationofoverlappingspeech.Thegeneralaudiounderstandingcapabilitiescoveraudio-,speech-,andmusic-captioning,temporalgroundingandsoundeventdetection,aswellasaudioquestionansweringandmultiple-choicereasoning.Thesetasksbroadentheapplicationscopefromrecognizingspokenwordstointerpretingspeakers,acousticevents,andtheirtemporalrelations.Toaccommodatedifferentdeploymentrequirements,thefamilyincludesvariantsforasynchronousfiletranscription,low-latencystreaming,interactivevoiceinput,andnon-streamingrecognition,withspeaker-diarizedtranscriptionandgeneralaudiounderstandingavailableincertainvariants.EvaluationsspanconventionalASR,multilingualanddialectalspeech,speaker-diarizedtranscription,andgeneralaudiounderstanding,demonstratingthecapabilitiesoftheQwen-Audio-3.1-ASRfamilyacrosstranscriptionandbroaderaudioanalysistasks.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2610\.28711

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.28711 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.28711 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.28711 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

@MaxForAI: If you are working on voice agents, you should try this project. A team from NTU, NUS, and Shanghai AI Lab released: Mega-ASR. This fully open-source ASR is built on Qwen3-ASR, aiming to break the long-standing bottleneck of ASR performance in noisy, reverberant, or other impaired real-world environments...

X AI KOLs Timeline

NTU, NUS, and Shanghai AI Lab jointly released Mega-ASR, a fully open-source ASR model built on Qwen3-ASR. Using the Voices-in-the-Wild-2M dataset and progressive acoustic-to-semantic optimization, it achieves up to 30% relative Word Error Rate (WER) reduction in real-world noisy environments. With only 1.7B parameters, it enables efficient inference on consumer-grade hardware.

@FeitengLi: Actually, these problems can be well solved: 1. Ditch whisper, switch to an ASR model. Qwen3-ASR is great with few hallucinations, and there are other ASR options. Whisper has many hallucinations and requires 30s segments. Qwen3-ASR gets more accurate with longer audio, supporting up to 20…

X AI KOLs Timeline

Recommends using Qwen3-ASR instead of Whisper to reduce hallucinations, using LattifAI tools for precise audio-text alignment and subtitle generation, and introducing their own OmniVAD-Kit project for voice activity detection.

@aigclink: Alibaba Tongyi Lab just dropped Fun-ASR 1.5—one industrial-grade model handles 30 languages, all 7 major Chinese dialect families + 20+ regional accents, even classical-poetry recitation. Dialect CER down 56.2 % vs last gen; 5 dialects top 90 % accuracy…

X AI KOLs Timeline

Alibaba Tongyi Lab releases Fun-ASR 1.5: a single model covering 30 languages, seven Chinese dialect groups and 20+ local accents; character-error rate in key dialect scenarios falls 56.2 %, with five dialects exceeding 90 % accuracy.

Qwen3-TTS Technical Report

Papers with Code Trending

The Qwen3-TTS technical report introduces a series of advanced multilingual text-to-speech models with voice cloning and controllable generation, featuring a dual-track LM architecture and specialized tokenizers for low-latency streaming.