{"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/tristounet-triplet-loss-for-speaker-turn","title":"TristouNet: Triplet Loss for Speaker Turn Embedding","arxiv_id":"1609.04301","date":"2016-09-14","proceeding":null,"authors":["Hervé Bredin"],"abstract":"TristouNet is a neural network architecture based on Long Short-Term Memory\nrecurrent networks, meant to project speech sequences into a fixed-dimensional\neuclidean space. Thanks to the triplet loss paradigm used for training, the\nresulting sequence embeddings can be compared directly with the euclidean\ndistance, for speaker comparison purposes. Experiments on short (between 500ms\nand 5s) speech turn comparison and speaker change detection show that\nTristouNet brings significant improvements over the current state-of-the-art\ntechniques for both tasks.","url_abs":"http://arxiv.org/abs/1609.04301v3","url_pdf":"http://arxiv.org/pdf/1609.04301v3.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":"tristounet-triplet-loss-for-speaker-turn","repo_url":"https://github.com/hbredin/TristouNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"tristounet-triplet-loss-for-speaker-turn","repo_url":"https://github.com/MarvinLvn/pyannote-audio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tristounet-triplet-loss-for-speaker-turn","repo_url":"https://github.com/jsalt-coml/babytrain_multilabel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"tristounet-triplet-loss-for-speaker-turn","repo_url":"https://github.com/jsalt-coml/pyannote-audio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tristounet-triplet-loss-for-speaker-turn","repo_url":"https://github.com/pyannote/pyannote-audio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tristounet-triplet-loss-for-speaker-turn","repo_url":"https://github.com/pyannote/pyannote-db-odessa-ami","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.04301","atlas_url":"https://app.syntology.ai/?focus=1609.04301","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}