{"id":"https://openalex.org/W2808682925","doi":"https://doi.org/10.21437/interspeech.2018-1308","title":"Unsupervised Word Segmentation from Speech with Attention","display_name":"Unsupervised Word Segmentation from Speech with Attention","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2808682925","doi":"https://doi.org/10.21437/interspeech.2018-1308","mag":"2808682925"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1308","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.12210/23240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001668256","display_name":"P. Godard","orcid":"https://orcid.org/0000-0002-5402-6033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Godard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043744108","display_name":"Marcely Zanon Boito","orcid":"https://orcid.org/0000-0003-0134-6719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcely Zanon Boito","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lucas Ondel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082937939","display_name":"Alexandre B\u00e9rard","orcid":"https://orcid.org/0009-0000-4848-6749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Berard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030615769","display_name":"Fran\u00e7ois Yvon","orcid":"https://orcid.org/0000-0002-7972-7442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Yvon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053823442","display_name":"Aline Villavicencio","orcid":"https://orcid.org/0000-0002-3731-9168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aline Villavicencio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040820339","display_name":"Laurent Besacier","orcid":"https://orcid.org/0000-0001-7411-9125"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent Besacier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5343,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91781497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2678","last_page":"2682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392533421516418},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6263710260391235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5545161366462708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5487294793128967},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.4946901500225067},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4737597107887268},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47228723764419556},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.41639935970306396},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19173556566238403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392533421516418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6263710260391235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5545161366462708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5487294793128967},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.4946901500225067},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4737597107887268},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47228723764419556},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.41639935970306396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19173556566238403},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-1308","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:150390","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:HAL:hal-01818092v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01818092","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2018, Sep 2018, Hyderabad, India. pp.2678-2682, &#x27E8;10.21437/Interspeech.2018-1308&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/23240","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/23240","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/23240","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/23240","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2105626703","https://openalex.org/W2514679778","https://openalex.org/W3026276030","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2026858810","https://openalex.org/W2384559435","https://openalex.org/W2393940967","https://openalex.org/W2337707338"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,25,33,43,56,68],"first":[3],"attempt":[4],"to":[5,19,52,81],"perform":[6],"attentional":[7,90],"word":[8,91],"segmen-tation":[9],"directly":[10],"from":[11],"the":[12,16,38,87],"speech":[13,54],"signal,":[14],"with":[15,40],"final":[17],"goal":[18],"automatically":[20],"identify":[21],"lexical":[22],"units":[23],"in":[24,37,42],"low-resource,":[26],"unwritten":[27],"language":[28,94],"(UL).":[29],"Our":[30],"methodology":[31],"assumes":[32],"pairing":[34],"between":[35],"recordings":[36],"UL":[39],"translations":[41],"well-resourced":[44],"language.":[45],"It":[46],"uses":[47,74],"Acoustic":[48],"Unit":[49],"Discovery":[50],"(AUD)":[51],"convert":[53],"into":[55],"sequence":[57],"of":[58,89],"pseudo-phones":[59],"that":[60],"is":[61],"segmented":[62],"using":[63],"neural":[64,69],"soft-alignments":[65],"produced":[66],"by":[67],"machine":[70],"translation":[71],"model.":[72],"Evaluation":[73],"an":[75],"actual":[76],"Bantu":[77],"UL,":[78],"Mboshi;":[79],"comparisons":[80],"monolingual":[82],"and":[83],"bilingual":[84],"baselines":[85],"illustrate":[86],"potential":[88],"segmentation":[92],"for":[93],"documentation.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
