{"id":"https://openalex.org/W1494243555","doi":"https://doi.org/10.21437/interspeech.2005-856","title":"Improving speech recognition using a data-driven approach","display_name":"Improving speech recognition using a data-driven approach","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W1494243555","doi":"https://doi.org/10.21437/interspeech.2005-856","mag":"1494243555"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-856","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/83177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048934331","display_name":"Guillermo Aradilla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillermo Aradilla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106182403","display_name":"Jithendra Vepa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jithendra Vepa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2202,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.88082197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3333","last_page":"3336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8294530510902405},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.813978910446167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.704289436340332},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5532262325286865},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5325654149055481},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5100053548812866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49426913261413574},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4785778522491455},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4364583194255829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43508797883987427},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.43276557326316833},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42495328187942505},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.41875913739204407},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41838544607162476},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11501973867416382},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09623309969902039}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294530510902405},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.813978910446167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.704289436340332},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5532262325286865},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5325654149055481},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5100053548812866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49426913261413574},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4785778522491455},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4364583194255829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43508797883987427},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.43276557326316833},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42495328187942505},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.41875913739204407},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41838544607162476},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11501973867416382},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09623309969902039},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2005-856","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:83177","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83177","pdf_url":"http://infoscience.epfl.ch/record/83177","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":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},{"id":"pmh:oai:infoscience.tind.io:83186","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/aradilla-rr-05-66","pdf_url":"http://publications.idiap.ch/downloads/reports/2005/rr05-66.pdf","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":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.173.5944","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.173.5944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/reports/2005/rr05-66.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:83186","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83186","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":null,"host_organization_name":null,"host_organization_lineage":[],"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.tind.io:83177","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83177","pdf_url":"http://infoscience.epfl.ch/record/83177","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":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1494243555.pdf","grobid_xml":"https://content.openalex.org/works/W1494243555.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W130324013","https://openalex.org/W156258841","https://openalex.org/W204308143","https://openalex.org/W1560013842","https://openalex.org/W1796349162","https://openalex.org/W2014239454","https://openalex.org/W2095959744","https://openalex.org/W2107223151","https://openalex.org/W2140383626","https://openalex.org/W2166163809","https://openalex.org/W4239875977","https://openalex.org/W4242662141","https://openalex.org/W4254295827","https://openalex.org/W4401371936"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W4245698648","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2405257913"],"abstract_inverted_index":{"In":[0],"this":[1,129],"paper,":[2],"we":[3,89,102],"investigate":[4,103],"the":[5,34,47,51,58,63,113,124,140,148,153,162],"possibility":[6],"of":[7,20,50,57,111,117],"enhancing":[8],"state-of-the-art":[9],"HMM-based":[10],"speech":[11,52],"recognition":[12,29,163],"systems":[13],"using":[14],"data-driven":[15,68],"techniques,":[16],"where":[17],"whole":[18],"set":[19],"training":[21],"utterances":[22],"is":[23,30],"used":[24],"as":[25,62,81],"reference":[26,120],"models":[27],"and":[28,77,85,98,108,119],"then":[31],"performed":[32],"through":[33],"well-known":[35],"template":[36],"matching":[37],"technique,":[38],"DTW.":[39],"This":[40],"approach":[41],"allows":[42],"us":[43,72],"to":[44,73,106,147],"better":[45,74],"capture":[46],"temporal":[48],"dynamics":[49],"signal":[53],"while":[54,155],"avoiding":[55],"some":[56],"HMM":[59,142],"assumptions":[60],"such":[61,67,80],"piecewise":[64],"stationarity.":[65],"Potentially,":[66],"techniques":[69],"also":[70],"allow":[71],"exploit":[75],"meta-data":[76],"environmental":[78],"information,":[79],"speaker,":[82],"gender,":[83],"accent":[84],"noise":[86],"conditions.":[87],"However,":[88],"cannot":[90],"entirely":[91],"abandon":[92],"HMMs,":[93],"which":[94],"are":[95],"very":[96],"powerful":[97],"scalable":[99],"models.":[100],"Thus,":[101],"one":[104],"way":[105],"combine":[107],"take":[109],"advantage":[110],"both":[112],"approaches,":[114],"combining":[115],"scores":[116],"HMMs":[118],"templates.":[121],"Experiments":[122],"on":[123],"Numbers95":[125],"database":[126],"showed":[127],"that":[128],"combination":[130],"yields":[131],"22\\%":[132],"relative":[133],"improvement":[134,160],"in":[135,161],"word":[136],"error":[137],"rate":[138],"over":[139],"baseline":[141],"performance.":[143],"Applying":[144],"K-means":[145],"clustering":[146],"acoustic":[149],"vectors":[150],"speeds":[151],"up":[152],"decoding,":[154],"still":[156],"retaining":[157],"a":[158],"significant":[159],"accuracy.":[164]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}