{"id":"https://openalex.org/W2152671307","doi":"https://doi.org/10.1109/icassp.2015.7178850","title":"An HMM-based formalism for automatic subword unit derivation and pronunciation generation","display_name":"An HMM-based formalism for automatic subword unit derivation and pronunciation generation","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W2152671307","doi":"https://doi.org/10.1109/icassp.2015.7178850","mag":"2152671307"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/206814","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044443491","display_name":"Marzieh Razavi","orcid":"https://orcid.org/0000-0001-6332-9661"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marzieh Razavi","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Valais, CH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Valais, CH","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6407,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86066946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"2","issue":null,"first_page":"4639","last_page":"4643"},"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":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.995199978351593,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9008476734161377},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8224120140075684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774817943572998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6924809813499451},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.6516848206520081},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.5834068655967712},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5778457522392273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5696817636489868},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.42075949907302856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36606353521347046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34108057618141174},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07543140649795532}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9008476734161377},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8224120140075684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774817943572998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6924809813499451},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.6516848206520081},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.5834068655967712},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5778457522392273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5696817636489868},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.42075949907302856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36606353521347046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34108057618141174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07543140649795532},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2015.7178850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.849.4617","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.849.4617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/206814/files/Razavi_ICASSP_2015.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:206814","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/206814","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:206814","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/206814","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W120415783","https://openalex.org/W308849112","https://openalex.org/W1526516369","https://openalex.org/W1534441687","https://openalex.org/W1580142630","https://openalex.org/W1590760721","https://openalex.org/W1618885279","https://openalex.org/W1918599710","https://openalex.org/W1957665339","https://openalex.org/W1964917299","https://openalex.org/W2045211645","https://openalex.org/W2065927558","https://openalex.org/W2077450519","https://openalex.org/W2090755665","https://openalex.org/W2098624096","https://openalex.org/W2100768664","https://openalex.org/W2125142492","https://openalex.org/W2128780426","https://openalex.org/W2143217142","https://openalex.org/W2158598479","https://openalex.org/W2170353620","https://openalex.org/W2401464865","https://openalex.org/W6635058605","https://openalex.org/W6635489705","https://openalex.org/W6636472884","https://openalex.org/W6640828828","https://openalex.org/W6675022971","https://openalex.org/W6678535732","https://openalex.org/W6681665012","https://openalex.org/W6683175690","https://openalex.org/W6685161094"],"related_works":["https://openalex.org/W3104532855","https://openalex.org/W2080578089","https://openalex.org/W2179005426","https://openalex.org/W4245698648","https://openalex.org/W3037446006","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,37],"novel":[3],"hidden":[4],"Markov":[5],"model":[6],"(HMM)":[7],"formalism":[8],"for":[9,96],"automatic":[10,61],"derivation":[11],"of":[12,55,101],"subword":[13,27,45],"units":[14,28,35],"and":[15],"pronunciation":[16],"generation":[17],"using":[18,41],"only":[19],"transcribed":[20],"speech":[21,62],"data.":[22],"In":[23],"this":[24],"approach,":[25],"the":[26,32,53,72,94],"are":[29,49],"derived":[30],"from":[31],"clustered":[33],"context-dependent":[34],"in":[36,52,79,92,99],"grapheme":[38],"based":[39,47,58],"system":[40],"maximum-likelihood":[42],"criterion.":[43],"The":[44,60],"unit":[46],"pronunciations":[48],"then":[50],"learned":[51],"framework":[54],"Kullback-Leibler":[56],"divergence":[57],"HMM.":[59],"recognition":[63],"(ASR)":[64],"experiments":[65],"on":[66],"WSJ0":[67],"English":[68],"corpus":[69],"show":[70],"that":[71],"approach":[73,88],"leads":[74],"to":[75,84],"12.7%":[76],"relative":[77],"reduction":[78],"word":[80],"error":[81],"rate":[82],"compared":[83],"grapheme-based":[85],"system.":[86],"Our":[87],"can":[89],"be":[90],"beneficial":[91],"reducing":[93],"need":[95],"expert":[97],"knowledge":[98],"development":[100],"ASR":[102],"as":[103,105],"well":[104],"text-to-speech":[106],"systems.":[107]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}