{"id":"https://openalex.org/W2407564530","doi":"https://doi.org/10.21437/interspeech.2014-364","title":"Noise-robust TTS speaker adaptation with statistics smoothing","display_name":"Noise-robust TTS speaker adaptation with statistics smoothing","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2407564530","doi":"https://doi.org/10.21437/interspeech.2014-364","mag":"2407564530"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-364","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070433127","display_name":"Langzhou Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Langzhou Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21846256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1519","last_page":"1523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9965000152587891,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/smoothing","display_name":"Smoothing","score":0.799545168876648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7727367281913757},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7290205955505371},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6280942559242249},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6104859113693237},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5294007062911987},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5271375179290771},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4874136745929718},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47115030884742737},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.45751234889030457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3370409607887268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3126222491264343},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12601619958877563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12060552835464478}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.799545168876648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727367281913757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7290205955505371},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6280942559242249},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6104859113693237},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5294007062911987},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5271375179290771},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4874136745929718},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47115030884742737},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45751234889030457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3370409607887268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3126222491264343},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12601619958877563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12060552835464478},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-364","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:788329","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/788329/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"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 or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"In":[0,19],"practical":[1],"scenarios":[2],"for":[3,165],"speaker":[4,35,84,124,175,185,194],"adaptation":[5,13],"of":[6,12,28,49,53,66,119,141,181,191],"speech":[7],"synthesis":[8,42,68,81],"systems,":[9],"the":[10,29,34,50,54,72,132,138,155,179,189,192],"quality":[11,156],"audio":[14,31],"data":[15],"may":[16],"be":[17,160],"poor.":[18],"these":[20],"situations,":[21],"it":[22,143],"is":[23,61,88,114,144],"necessary":[24],"to":[25,32,39,58,62,146,176],"make":[26],"use":[27],"available":[30],"capture":[33],"attributes,":[36],"whilst":[37],"aiming":[38],"obtain":[40],"a":[41,64,98,106,111,117,182],"voice":[43],"which":[44,71],"does":[45],"not":[46],"have":[47],"any":[48],"lowquality":[51],"attributes":[52],"audio.":[55],"One":[56],"approach":[57,100],"achieving":[59],"this":[60,78,103,123],"define":[63],"sub-space":[65],"parametric":[67],"parameters":[69],"in":[70,91],"adapted":[73],"system":[74],"must":[75],"lie.":[76],"Though":[77],"yields":[79],"reasonable":[80,183],"quality,":[82],"target":[83,108,133],"similarity":[85,148,158,170],"degrades.":[86],"Quality":[87],"also":[89],"affected":[90],"severe":[92,166],"noise":[93,167],"conditions.":[94,168],"This":[95],"paper":[96],"describes":[97],"smoothing":[99],"that":[101,153],"addresses":[102],"problem.":[104],"For":[105],"noisy":[107],"speaker,":[109,177],"first":[110],"'similar":[112],"speaker'":[113],"selected":[115],"from":[116,122,131,174],"database":[118],"speakers.":[120],"Statistics":[121],"are":[125],"then":[126],"smoothed":[127],"with":[128],"those":[129],"obtained":[130],"speaker.":[134],"By":[135],"appropriately":[136],"combining":[137],"two":[139],"sources":[140],"information,":[142],"possible":[145],"balance":[147],"and":[149,157,188],"quality.":[150],"Results":[151],"indicate":[152],"both":[154],"can":[159],"improved":[161],"by":[162],"smoothing,":[163],"especially":[164],"The":[169],"performance,":[171],"however,":[172],"varies":[173],"indicating":[178],"importance":[180],"automatic":[184],"selection":[186],"method":[187],"coverage":[190],"candidate":[193],"pool.":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}