{"corpus_id":6277347,"paper_sha":"aca94a780d3994839663ff743d3319d920db9297","doi":"10.1162/tacl_a_00146","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":1778492285,"dblp_id":"journals/tacl/LeeOG15","acl_id":"Q15-1028","title":"Unsupervised Lexicon Discovery from Acoustic Input","year":2015,"publication_date":"2015-07-17","venue":"Transactions of the Association for Computational Linguistics","journal":{"name":"Transactions of the Association for Computational Linguistics","pages":"389-403","volume":"3"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":null,"s2_fields_of_study":["Linguistics","Computer Science"],"reference_count":58,"citation_count":91,"influential_citation_count":8,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00146","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/aca94a780d3994839663ff743d3319d920db9297","s2_open_access_license":"CCBY","s2_open_access_status":"GOLD","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"We present a model of unsupervised phonological lexicon discovery—the problem of simultaneously learning phoneme-like and word-like units from acoustic input. Our model builds on earlier models of unsupervised phone-like unit discovery from acoustic data (Lee and Glass, 2012), and unsupervised symbolic lexicon discovery using the Adaptor Grammar framework (Johnson et al., 2006), integrating these earlier approaches using a probabilistic model of phonological variation. We show that the model is competitive with state-of-the-art spoken term discovery systems, and present analyses exploring the model’s behavior and the kinds of linguistic structures it learns.","claims":[{"public_id":"cl_7bcf236c50471c6665544bcc79096fb7","status":"active","text":"The model integrates unsupervised phone-like unit discovery and unsupervised symbolic lexicon discovery using a probabilistic model of phonological variation.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_7bcf236c50471c6665544bcc79096fb7"},{"public_id":"cl_7ef083385e573e2d664ba04eb0cc95d2","status":"active","text":"The model is competitive with state-of-the-art spoken term discovery systems.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_7ef083385e573e2d664ba04eb0cc95d2"},{"public_id":"cl_28ccd56aa3f73ddd6ed8c12709896ee2","status":"active","text":"The model simultaneously learns phoneme-like and word-like units from acoustic input.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_28ccd56aa3f73ddd6ed8c12709896ee2"}],"concepts":[{"public_id":"co_08a86b4b3fbdcbde321ad0ab25503d30","status":"active","name":"probabilistic model of phonological variation","description":"A probabilistic model that accounts for phonological variation, used to integrate the phone-like and symbolic lexicon discovery approaches.","types":["model"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_08a86b4b3fbdcbde321ad0ab25503d30"},{"public_id":"co_12065f8d8a575ed69e937d1d503e8855","status":"active","name":"unsupervised phone-like unit discovery","description":"A method for discovering phone-like units from acoustic data without supervision, based on earlier work by Lee and Glass (2012).","types":["method"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_12065f8d8a575ed69e937d1d503e8855"},{"public_id":"co_ad1df3dae4ad49f3a4e89bde2365f73e","status":"active","name":"word-like units","description":"Units resembling words that are learned from acoustic input by the model.","types":["linguistic unit"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_ad1df3dae4ad49f3a4e89bde2365f73e"},{"public_id":"co_b6c6828b9594b16a441381afd5aff35a","status":"active","name":"spoken term discovery systems","description":"State-of-the-art systems for discovering spoken terms from acoustic input, used as a baseline for comparison.","types":["baseline"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_b6c6828b9594b16a441381afd5aff35a"},{"public_id":"co_d4b6051cc05984ac70d510c32b65de43","status":"active","name":"unsupervised symbolic lexicon discovery","description":"A method for discovering symbolic lexicon units without supervision, using the Adaptor Grammar framework (Johnson et al., 2006).","types":["method"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_d4b6051cc05984ac70d510c32b65de43"},{"public_id":"co_da53f046e4944186027ab9b6620480a8","status":"active","name":"acoustic input","description":"Raw acoustic signal data used as input to the model for learning linguistic units.","types":["data"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_da53f046e4944186027ab9b6620480a8"},{"public_id":"co_e91c9101aa0c5f3a7bc690456a1b79cf","status":"active","name":"phoneme-like units","description":"Units resembling phonemes that are learned from acoustic input by the model.","types":["linguistic unit"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_e91c9101aa0c5f3a7bc690456a1b79cf"}],"external_ids":{"DOI":"10.1162/tacl_a_00146","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":1778492285,"DBLP":"journals/tacl/LeeOG15","ACL":"Q15-1028"},"open_access":{"is_open_access":true,"pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00146","landing_url":"https://www.semanticscholar.org/paper/aca94a780d3994839663ff743d3319d920db9297","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBY","status":"GOLD","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":638940,"paper_uid":"5cc6dae1-c5c1-46d1-8c69-efefb5f28339","canonical_identity":{"paper_id":638940,"paper_uid":"5cc6dae1-c5c1-46d1-8c69-efefb5f28339","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/6277347"}