{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-efficient-representations-for-3","title":"Learning Efficient Representations for Keyword Spotting with Triplet Loss","arxiv_id":"2101.04792","date":"2021-01-12","proceeding":"SPECOM 2021","authors":["Roman Vygon","Nikolay Mikhaylovskiy"],"abstract":"In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most no-tably, person reidentification. On the other hand, in the area of speech recognition the metric embeddings generated by the triplet loss are rarely used even for classification problems. We fill this gap showing that a combination of two representation learning techniques: a triplet loss-based embedding and a variant of kNN for classification instead of cross-entropy loss significantly (by 26% to 38%) improves the classification accuracy for convolutional networks on a LibriSpeech-derived LibriWords datasets. To do so, we propose a novel phonetic similarity based triplet mining approach. We also improve the current best published SOTA for Google Speech Commands dataset V1 10+2 -class classification by about 34%, achieving 98.55% accuracy, V2 10+2-class classification by about 20%, achieving 98.37% accuracy, and V2 35-class classification by over 50%, achieving 97.0% accuracy.","url_abs":"https://arxiv.org/abs/2101.04792v4","url_pdf":"https://arxiv.org/pdf/2101.04792v4.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":"learning-efficient-representations-for-3","repo_url":"https://github.com/roman-vygon/triplet_loss_kws","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"keyword-spotting","task_name":"Keyword Spotting"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keyword-spotting-on-google-speech-commands","task":"Keyword Spotting","dataset":"Google Speech Commands","model":"TripletLoss-res15","rank_in_archive_order":1,"of":42,"metrics":{"Google Speech Commands V1 12":"98.56","Google Speech Commands V2 12":"98.37","Google Speech Commands V2 35":"97.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.04792","atlas_url":"https://app.syntology.ai/?focus=2101.04792","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2101.04792"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2101.04792\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2101.04792"},"call":"get_concepts_for_paper(arxiv_id=\"2101.04792\")"}],"by_repo":[{"repo":"roman-vygon/triplet_loss_kws","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0ec372dac4e04dff84882b5c64283f8f1fd9d766939ca53d2f825c7402517367","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}