Papers › Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale...

Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

14 Nov 2023arXiv:2311.07919archive 2025-07-28

Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, Jingren Zhou

Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress in this field. Consequently, most existing works have only been able to support a limited range of interaction capabilities. In this paper, we develop the Qwen-Audio model and address this limitation by scaling up audio-language pre-training to cover over 30 tasks and various audio types, such as human speech, natural sounds, music, and songs, to facilitate universal audio understanding abilities. However, directly co-training all tasks and datasets can lead to interference issues, as the textual labels associated with different datasets exhibit considerable variations due to differences in task focus, language, granularity of annotation, and text structure. To overcome the one-to-many interference, we carefully design a multi-task training framework by conditioning on a sequence of hierarchical tags to the decoder for encouraging knowledge sharing and avoiding interference through shared and specified tags respectively. Remarkably, Qwen-Audio achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning, surpassing its counterparts. Building upon the capabilities of Qwen-Audio, we further develop Qwen-Audio-Chat, which allows for input from various audios and text inputs, enabling multi-turn dialogues and supporting various audio-central scenarios.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 5 ran (3 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qwenlm/qwen-audio officialmentioned in papermentioned on GitHubpytorchSyntology: 7 samples, 5 ran (2 instrument-failed) · 2 unverified report
alibaba-damo-academy/FunASR pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation (arXiv:2312.15185; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
2unverified

Licence: 7 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from qwenlm/qwen-audio. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

qwenlm/qwen-audio official repository 7 samples, 5 ran (2 instrument-failed) · 2 unverified
collate_fn in 500 papers eval_audio/evaluate_aqa.py ran · our draft was wrong licence not identified · pointer only · fb0866cc3d285415 · report fixture: signature inputs:list/1/dict, tokenizer:callable/0/? · returned tuple · level recorded 2026-09-22
dequantize_cache_torch modeling_qwen.py ran · honoured contract fingerprinted licence not identified · pointer only · d9db9f86b30f9ac0 · report fixture: signature qdata:Tensor/2/int, scale:Tensor/2/float, zero:Tensor/2/int · returned Tensor · level recorded 2026-09-22
exact_div in 9 papers audio.py ran · honoured contract fingerprinted licence not identified · pointer only · 6e0808fc4828513a · report fixture: signature x:int/0/int, y:int/0/int · returned int · level recorded 2026-09-22
get_T_after_cnn audio.py ran · honoured contract fingerprinted licence not identified · pointer only · 3bca85a509d7b2a6 · report fixture: signature L_in:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
quantize_cache_v modeling_qwen.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 1fec7a76f0d171a6 · report fixture: signature fdata:Tensor/4/float, bits:int/0/int, qmax:Tensor/0/float, qmin:Tensor/0/float · returned tuple · level recorded 2026-09-22
load_bytesio_audio audio.py unverified licence not identified · pointer only · 3dbcbc5b3f57546c · report

Tasks

Acoustic Scene ClassificationAudio ClassificationAudio captioningAutomatic Speech Recognition (ASR)DecoderEmotion Recognition in ConversationInstruction FollowingSpeech Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Acoustic Scene Classification CochlScene Qwen-Audio 1:1 Accuracy 0.795 #2 of 2 Archive leaderboard report
Acoustic Scene Classification TUT Acoustic Scenes 2017 Qwen-Audio 1:1 Accuracy 0.649 #1 of 1 Archive leaderboard report
Audio Classification VocalSound Qwen-Audio Accuracy 92.89 #2 of 2 Archive leaderboard report
Audio captioning Clotho Qwen-Audio CIDEr 0.441 #7 of 11 Archive leaderboard report
Audio captioning Clotho Qwen-Audio SPICE 0.136 #7 of 11 Archive leaderboard report
Audio captioning Clotho Qwen-Audio SPIDEr 0.288 #7 of 11 Archive leaderboard report
Emotion Recognition in Conversation MELD Qwen-Audio Accuracy 55.70 #68 of 68 Archive leaderboard report
Speech Recognition AISHELL-1 Qwen-Audio Word Error Rate (WER) 1.29 #3 of 18 Archive leaderboard report
Speech Recognition AISHELL-2 Test Android Qwen-Audio Word Error Rate (WER) 3.3 #1 of 1 Archive leaderboard report
Speech Recognition AISHELL-2 Test IOS Qwen-Audio Word Error Rate (WER) 3.1 #1 of 1 Archive leaderboard report
Speech Recognition AISHELL-2 Test Mic Qwen-Audio Word Error Rate (WER) 3.3 #1 of 1 Archive leaderboard report
Speech Recognition LibriSpeech test-clean Qwen-Audio Word Error Rate (WER) 2.0 #24 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other Qwen-Audio Word Error Rate (WER) 4.2 #22 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections