{"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/multi-task-learning-of-speech-and-speaker","title":"Towards multi-task learning of speech and speaker recognition","arxiv_id":"2302.12773","date":"2023-02-24","proceeding":null,"authors":["Nik Vaessen","David A. van Leeuwen"],"abstract":"We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix speaker and speech information in the output sequence as well as different optimization strategies. Our multi-task learning networks can produce a shared speaker and speech embedding, which on first glance achieve a performance comparable to separate single-task models. However, we show that the multi-task networks have strongly degraded performance on out-of-distribution evaluation data compared to the single-task models. Code and model checkpoints are available at https://github.com/nikvaessen/disjoint-mtl","url_abs":"https://arxiv.org/abs/2302.12773v2","url_pdf":"https://arxiv.org/pdf/2302.12773v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"multi-task-learning-of-speech-and-speaker","repo_url":"https://github.com/nikvaessen/2022-repo-mt-w2v2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"multi-task-learning-of-speech-and-speaker","repo_url":"https://github.com/nikvaessen/disjoint-mtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}