{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/w2v-bert-combining-contrastive-learning-and","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","arxiv_id":"2108.06209","date":"2021-08-07","proceeding":null,"authors":["Yu-An Chung","Yu Zhang","Wei Han","Chung-Cheng Chiu","James Qin","Ruoming Pang","Yonghui Wu"],"abstract":"Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines contrastive learning and MLM, where the former trains the model to discretize input continuous speech signals into a finite set of discriminative speech tokens, and the latter trains the model to learn contextualized speech representations via solving a masked prediction task consuming the discretized tokens. In contrast to existing MLM-based speech pre-training frameworks such as HuBERT, which relies on an iterative re-clustering and re-training process, or vq-wav2vec, which concatenates two separately trained modules, w2v-BERT can be optimized in an end-to-end fashion by solving the two self-supervised tasks~(the contrastive task and MLM) simultaneously. Our experiments show that w2v-BERT achieves competitive results compared to current state-of-the-art pre-trained models on the LibriSpeech benchmarks when using the Libri-Light~60k corpus as the unsupervised data. In particular, when compared to published models such as conformer-based wav2vec~2.0 and HuBERT, our model shows~5\\% to~10\\% relative WER reduction on the test-clean and test-other subsets. When applied to the Google's Voice Search traffic dataset, w2v-BERT outperforms our internal conformer-based wav2vec~2.0 by more than~30\\% relatively.","url_abs":"https://arxiv.org/abs/2108.06209v2","url_pdf":"https://arxiv.org/pdf/2108.06209v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"w2v-bert-combining-contrastive-learning-and","repo_url":"https://github.com/RoganInglis/AudioLM/tree/main/src/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"w2v-bert-combining-contrastive-learning-and","repo_url":"https://github.com/facebookresearch/fairseq/tree/ust/examples/w2vbert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"w2v-bert-combining-contrastive-learning-and","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/1/wav2vec2_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"w2v-bert-combining-contrastive-learning-and","repo_url":"https://github.com/wenet-e2e/wenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-representation-learning","task_name":"Speech Representation Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"w2v-BERT XXL","rank_in_archive_order":5,"of":64,"metrics":{"Word Error Rate (WER)":"1.4"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"w2v-BERT XXL","rank_in_archive_order":3,"of":53,"metrics":{"Word Error Rate (WER)":"2.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.06209","atlas_url":"https://app.syntology.ai/?focus=2108.06209","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}