{"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/wav2seq-pre-training-speech-to-text-encoder","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","arxiv_id":"2205.01086","date":"2022-05-02","proceeding":null,"authors":["Felix Wu","Kwangyoun Kim","Shinji Watanabe","Kyu Han","Ryan Mcdonald","Kilian Q. Weinberger","Yoav Artzi"],"abstract":"We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task -- transcribing audio inputs into pseudo subword sequences. This process stands on its own, or can be applied as low-cost second-stage pre-training. We experiment with automatic speech recognition (ASR), spoken named entity recognition, and speech-to-text translation. We set new state-of-the-art results for end-to-end spoken named entity recognition, and show consistent improvements on 20 language pairs for speech-to-text translation, even when competing methods use additional text data for training. Finally, on ASR, our approach enables encoder-decoder methods to benefit from pre-training for all parts of the network, and shows comparable performance to highly optimized recent methods.","url_abs":"https://arxiv.org/abs/2205.01086v1","url_pdf":"https://arxiv.org/pdf/2205.01086v1.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":"wav2seq-pre-training-speech-to-text-encoder","repo_url":"https://github.com/asappresearch/wav2seq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"speech-to-text-translation","task_name":"Speech-to-Text Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-on-slue","task":"Named Entity Recognition (NER)","dataset":"SLUE","model":"Wav2Seq (from HuBERT-large)","rank_in_archive_order":3,"of":13,"metrics":{"F1 (%)":"65.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.01086","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}