{"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/query-by-example-search-with-discriminative","title":"Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings","arxiv_id":"1706.03818","date":"2017-06-12","proceeding":null,"authors":["Shane Settle","Keith Levin","Herman Kamper","Karen Livescu"],"abstract":"Query-by-example search often uses dynamic time warping (DTW) for comparing\nqueries and proposed matching segments. Recent work has shown that comparing\nspeech segments by representing them as fixed-dimensional vectors --- acoustic\nword embeddings --- and measuring their vector distance (e.g., cosine distance)\ncan discriminate between words more accurately than DTW-based approaches. We\nconsider an approach to query-by-example search that embeds both the query and\ndatabase segments according to a neural model, followed by nearest-neighbor\nsearch to find the matching segments. Earlier work on embedding-based\nquery-by-example, using template-based acoustic word embeddings, achieved\ncompetitive performance. We find that our embeddings, based on recurrent neural\nnetworks trained to optimize word discrimination, achieve substantial\nimprovements in performance and run-time efficiency over the previous\napproaches.","url_abs":"http://arxiv.org/abs/1706.03818v1","url_pdf":"http://arxiv.org/pdf/1706.03818v1.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":"query-by-example-search-with-discriminative","repo_url":"https://github.com/kamperh/recipe_semantic_flickraudio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.03818","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}