WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Open accessThe DOI matches its Crossref record; 109 of the 109 references it cites were found in a registry or an index.
Abstract
Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. To tackle the problem, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM jointly learns masked speech prediction and denoising in pre-training. By this means, WavLM does not only keep the speech content modeling capability by the masked speech prediction, but also improves the potential to non-ASR tasks by the speech denoising. In addition, WavLM employs gated relative position bias for the Transformer structure to better capture the sequence ordering of input speech. We also scale up the training dataset from 60 k hours to 94 k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Experimental results indicate that WavLM outperforms all preceding models on these tasks, pointing to the promise and potential of deep learning in enhancing SER.”
From A Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face (2023) · cites this paper as [57]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Most recently, Chen et al. introduced WavLM [57], the first universal speech pre-training model capable of being applied to a broad range of tasks, including speaker recognition, speech recognition, and emotion recognition.”
From A Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face (2023) · cites this paper as [57]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, features from current speech self-supervised models are inadequate for multi-speaker tasks [9], including audio deepfake detection.”
From Audio Deepfake Detection With Self-Supervised WavLM And Multi-Fusion Attentive Classifier (2024) · cites this paper as [9]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Layer-wise analyses of self-supervised speech models showthat acoustic and speaker-related cues concentrate in lower and intermediate layers while deeper layers drift toward lexical and semantic content [19, 20], and that a learnable combination of all layers consistently outperforms the last-layer representation across diverse speech tasks [21].”
From MOSS-Audio Technical Report (2026) · cites this paper as [20]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Attributed to the masked speech prediction and denoising training, WavLM has the potential to learn nonASR features, including complex acoustic environments and speaker-related information and had demonstrated improved performance on certain non-ASR tasks.”
From Audio Deepfake Detection With Self-Supervised WavLM And Multi-Fusion Attentive Classifier (2024) · cites this paper as [9]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Research works printed but not linked: 1
- 10.1109/ICASSP40776.2020.9053176 · DOI
Cited by
A comprehensive survey on applications of transformers for deep learning tasks
Islam, S., Elmekki, H., Elsebai, A., Bentahar, J., Drawel, N., Rjoub, G., & Pedrycz, W. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122666 · Cited by 487
CLAP Learning Audio Concepts from Natural Language Supervision
Elizalde, B., Deshmukh, S., Ismail, M. A., & Wang, H. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10095889 · Cited by 449
A review of deep learning techniques for speech processing
Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., & Poria, S. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101869 · Cited by 389
Self-supervised speech representation learning: A review
Mohamed, A., Lee, H.-Y., Borgholt, L., Havtorn, J. D., Edin, J., Igel, C., Kirchhoff, K., Li, S.-W., Livescu, K., Maaløe, L., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3207050 · Cited by 372
“The WavLM model achieved substantial improvements on the speech separation, speaker verification and speaker diarization tasks in the SUPERB benchmark, while also performing well on many other tasks compared to HuBERT and wav2vec 2.0. d) data2vec: Motivated by the success of using an exponential moving average (EMA) t…”
BackgroundMethodInfluentialWhisperX: Time-Accurate Speech Transcription of Long-Form Audio
Bain, M., Huh, J., Han, T., & Zisserman, A. (2023) · INTERSPEECH 2023 · doi:10.21437/interspeech.2023-78 · Cited by 337
Metadata
- Authors
- Chen, S., Wang, C., Chen, Z., Wu, Y., Liu, S., Chen, Z., Li, J., Kanda, N., Yoshioka, T., Xiao, X., Wu, J., Zhou, L., Ren, S., Qian, Y., Qian, Y., Wu, J., Zeng, M., Yu, X., & Wei, F.
- Affiliations
- Harbin Institute of Technology (CN)
- Nankai University (CN)
- Microsoft (United States) (US)
- Microsoft Research Asia (China) (CN)
- ORCID
- Venue
- IEEE Journal of Selected Topics in Signal Processing
- Published
- 2022-10
- Volume
- 16
- Issue
- 6
- Pages
- 1505-1518
- ISSN
- 1932-4553 (ISSN-L)
- 1941-0484
- OpenAlex
- W3209984917
- Cited by
- 1,926
- References
- 108
- Citations by year
- 2026: 472 · 2025: 654 · 2024: 412 · 2023: 306 · 2022: 82
- FWCI
- 119.62
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Journal of Selected Topics in Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- WavLM, self-supervised pre-training, speech representation learning, speech denoising, transformer models, speaker identity, paralinguistic features
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing. https://app.cochat.ai/papers/10.1109/jstsp.2022.3188113
- The paper
- Chen, S., Wang, C., Chen, Z., Wu, Y., Liu, S., Chen, Z., Li, J., Kanda, N., Yoshioka, T., Xiao, X., Wu, J., Zhou, L., Ren, S., Qian, Y., Qian, Y., Wu, J., Zeng, M., Yu, X., & Wei, F. (2022). WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing. IEEE Journal of Selected Topics in Signal Processing. https://doi.org/10.1109/jstsp.2022.3188113
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.