{"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/sumformer-a-linear-complexity-alternative-to","title":"SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding","arxiv_id":"2307.07421","date":"2023-07-12","proceeding":null,"authors":["Titouan Parcollet","Rogier Van Dalen","Shucong Zhang","Sourav Bhattacharya"],"abstract":"Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down inference and training and increasing memory consumption. Cheaper alternatives to self-attention for ASR have been developed, but they fail to consistently reach the same level of accuracy. This paper, therefore, proposes a novel linear-time alternative to self-attention. It summarises an utterance with the mean over vectors for all time steps. This single summary is then combined with time-specific information. We call this method \"SummaryMixing\". Introducing SummaryMixing in state-of-the-art ASR models makes it feasible to preserve or exceed previous speech recognition performance while making training and inference up to 28% faster and reducing memory use by half.","url_abs":"https://arxiv.org/abs/2307.07421v3","url_pdf":"https://arxiv.org/pdf/2307.07421v3.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":"sumformer-a-linear-complexity-alternative-to","repo_url":"https://github.com/samsunglabs/summarymixing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.07421","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}