{"id":"https://openalex.org/W149249243","doi":"https://doi.org/10.21437/eurospeech.1999-57","title":"On combining vocal tract length normalisation and speaker adaptation for noise robust speech recognition","display_name":"On combining vocal tract length normalisation and speaker adaptation for noise robust speech recognition","publication_year":1999,"publication_date":"1999-09-05","ids":{"openalex":"https://openalex.org/W149249243","doi":"https://doi.org/10.21437/eurospeech.1999-57","mag":"149249243"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1999-57","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-57","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009715421","display_name":"Ramalingam Hariharan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106018","display_name":"Nokia (Netherlands)","ror":"https://ror.org/01resg468","country_code":"NL","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210106018"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ramalingam Hariharan","raw_affiliation_strings":["Nokia,#TAB#"],"affiliations":[{"raw_affiliation_string":"Nokia,#TAB#","institution_ids":["https://openalex.org/I4210106018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032298742","display_name":"Olli Viikki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olli Viikki","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009715421"],"corresponding_institution_ids":["https://openalex.org/I4210106018"],"apc_list":null,"apc_paid":null,"fwci":1.0195,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79190959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"215","last_page":"218"},"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/vocal-tract","display_name":"Vocal tract","score":0.8683963418006897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7731896638870239},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.764399528503418},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.639313280582428},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5917059779167175},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5664392113685608},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5342435240745544},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5155556201934814},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5114744901657104},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4441496431827545},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4424492120742798},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4094458520412445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3705952763557434},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09736877679824829}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8683963418006897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731896638870239},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.764399528503418},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.639313280582428},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5917059779167175},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5664392113685608},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5342435240745544},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5155556201934814},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5114744901657104},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4441496431827545},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4424492120742798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4094458520412445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3705952763557434},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09736877679824829},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1999-57","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-57","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W92958402","https://openalex.org/W1505035441","https://openalex.org/W1599512239","https://openalex.org/W2100969003","https://openalex.org/W2104924374","https://openalex.org/W2106119541","https://openalex.org/W2111918028","https://openalex.org/W2140567543","https://openalex.org/W2146871184","https://openalex.org/W2151899309","https://openalex.org/W2164720542"],"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/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2740630172","https://openalex.org/W2938358845"],"abstract_inverted_index":{"This":[0],"paper":[1,51],"investigates":[2],"the":[3,42,47,68,100,106,110],"combination":[4],"of":[5],"vocal":[6,58],"tract":[7,59],"length":[8,60],"normalisation":[9,69,88],"and":[10,35,77],"speaker":[11,34,86,116],"adaptation":[12,37,117,137],"in":[13,112],"connected":[14,101],"digit":[15,102],"recognition.":[16],"In":[17],"particular,":[18],"we":[19],"focus":[20],"on":[21,41,99,120],"performing":[22],"this":[23],"task":[24],"under":[25],"a":[26],"continuously":[27],"varying":[28],"car":[29],"noise":[30],"environment.":[31],"Continuous":[32],"supervised":[33],"environment":[36],"is":[38,118,138],"carried":[39],"out":[40],"test":[43],"data":[44],"according":[45],"to":[46,56],"Bayesian":[48,115],"framework.":[49],"The":[50,62,124],"also":[52,81],"evaluates":[53],"various":[54],"approaches":[55],"implement":[57],"normalisation.":[61,95],"best":[63],"performance":[64,125],"was":[65,70,80,127],"obtained":[66],"when":[67],"performed":[71,119],"during":[72,84],"both":[73],"initial":[74],"speaker-independent":[75],"training":[76],"testing.":[78],"It":[79],"noticed":[82],"that,":[83],"testing,":[85],"specific":[87,94],"produced":[89],"better":[90],"results":[91,98],"than":[92],"utterance":[93],"Our":[96],"experimental":[97],"database":[103],"show":[104],"that":[105],"joint":[107],"approach":[108],"outperforms":[109],"system":[111],"which":[113],"on-line":[114],"HMM":[121],"mean":[122],"parameters.":[123],"gain":[126],"particularly":[128],"high":[129],"with":[130],"so":[131],"called":[132],"outlier":[133],"speakers":[134],"for":[135],"whom":[136],"truly":[139],"needed.":[140]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}