{"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/tempadacos-learning-temporally-structured","title":"TACos: Learning Temporally Structured Embeddings for Few-Shot Keyword Spotting with Dynamic Time Warping","arxiv_id":"2305.10816","date":"2023-05-18","proceeding":null,"authors":["Kevin Wilkinghoff","Alessia Cornaggia-Urrigshardt"],"abstract":"To segment a signal into blocks to be analyzed, few-shot keyword spotting (KWS) systems often utilize a sliding window of fixed size. Because of the varying lengths of different keywords or their spoken instances, choosing the right window size is a problem: A window should be long enough to contain all necessary information needed to recognize a keyword but a longer window may contain irrelevant information such as multiple words or noise and thus makes it difficult to reliably detect on- and offsets of keywords. We propose TACos, a novel angular margin loss for deriving two-dimensional embeddings that retain temporal properties of the underlying speech signal. In experiments conducted on KWS-DailyTalk, a few-shot KWS dataset presented in this work, using these embeddings as templates for dynamic time warping is shown to outperform using other representations or a sliding window and that using time-reversed segments of the keywords during training improves the performance.","url_abs":"https://arxiv.org/abs/2305.10816v3","url_pdf":"https://arxiv.org/pdf/2305.10816v3.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":"tempadacos-learning-temporally-structured","repo_url":"https://github.com/wilkinghoff/kws-dailytalk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"keyword-spotting","task_name":"Keyword Spotting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}