{"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/unsupervised-word-segmentation-using-k","title":"Unsupervised Word Segmentation using K Nearest Neighbors","arxiv_id":"2204.13094","date":"2022-04-27","proceeding":null,"authors":["Tzeviya Sylvia Fuchs","Yedid Hoshen","Joseph Keshet"],"abstract":"In this paper, we propose an unsupervised kNN-based approach for word segmentation in speech utterances. Our method relies on self-supervised pre-trained speech representations, and compares each audio segment of a given utterance to its K nearest neighbors within the training set. Our main assumption is that a segment containing more than one word would occur less often than a segment containing a single word. Our method does not require phoneme discovery and is able to operate directly on pre-trained audio representations. This is in contrast to current methods that use a two-stage approach; first detecting the phonemes in the utterance and then detecting word-boundaries according to statistics calculated on phoneme patterns. Experiments on two datasets demonstrate improved results over previous single-stage methods and competitive results on state-of-the-art two-stage methods.","url_abs":"https://arxiv.org/abs/2204.13094v1","url_pdf":"https://arxiv.org/pdf/2204.13094v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"unsupervised-word-segmentation-using-k","repo_url":"https://github.com/mlspeech/gradseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.13094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13094"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mlspeech/gradseg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":4,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":7,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5cf9b5e522af96d5","entry":"boundaries_to_intervals","repo":"mlspeech/gradseg","repo_kind":"listed","path":"eval_segmentation.py","file_url":"https://github.com/mlspeech/gradseg/blob/HEAD/eval_segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cf9b5e522af96d5"}},{"code_sha256_prefix":"a73490164e4bb95c","entry":"get_emb","repo":"mlspeech/gradseg","repo_kind":"listed","path":"data_loader.py","file_url":"https://github.com/mlspeech/gradseg/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a73490164e4bb95c"}},{"code_sha256_prefix":"a5c12d20fafb384f","entry":"get_grad_mag","repo":"mlspeech/gradseg","repo_kind":"listed","path":"grad_segmenter.py","file_url":"https://github.com/mlspeech/gradseg/blob/HEAD/grad_segmenter.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5c12d20fafb384f"}},{"code_sha256_prefix":"54dbd7b3ecbb6448","entry":"get_intervals_from_dir","repo":"mlspeech/gradseg","repo_kind":"listed","path":"eval_segmentation.py","file_url":"https://github.com/mlspeech/gradseg/blob/HEAD/eval_segmentation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54dbd7b3ecbb6448"}},{"code_sha256_prefix":"4e7fcd91f3f7615d","entry":"get_seg","repo":"mlspeech/gradseg","repo_kind":"listed","path":"grad_segmenter.py","file_url":"https://github.com/mlspeech/gradseg/blob/HEAD/grad_segmenter.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e7fcd91f3f7615d"}},{"code_sha256_prefix":"bdd3717607f29767","entry":"intervals_to_boundaries","repo":"mlspeech/gradseg","repo_kind":"listed","path":"eval_segmentation.py","file_url":"https://github.com/mlspeech/gradseg/blob/HEAD/eval_segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdd3717607f29767"}},{"code_sha256_prefix":"364cd200bab3e807","entry":"embed","repo":"mlspeech/gradseg","repo_kind":"listed","path":"data_loader.py","file_url":"https://github.com/mlspeech/gradseg/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"364cd200bab3e807"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}