{"id":"https://openalex.org/W39836914","doi":"https://doi.org/10.21437/interspeech.2004-458","title":"A family-of-models approach to HMM-based segmentation for unit selection speech synthesis","display_name":"A family-of-models approach to HMM-based segmentation for unit selection speech synthesis","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W39836914","doi":"https://doi.org/10.21437/interspeech.2004-458","mag":"39836914"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-458","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5013132605","display_name":"John Kominek","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Kominek","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W Black","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.3127,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88834701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1385","last_page":"1388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9954000115394592,"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":0.98580002784729,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7545806169509888},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7459657192230225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7173463106155396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7117736339569092},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6291557550430298},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5507548451423645},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49824023246765137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4877408444881439},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.48650306463241577},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.47300463914871216},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47182804346084595},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4336310625076294},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.4122385084629059},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40641075372695923},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11871910095214844}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7545806169509888},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7459657192230225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173463106155396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7117736339569092},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6291557550430298},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5507548451423645},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49824023246765137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4877408444881439},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.48650306463241577},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.47300463914871216},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47182804346084595},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4336310625076294},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.4122385084629059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40641075372695923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11871910095214844},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-458","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W97413234","https://openalex.org/W2147333232"],"related_works":["https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2147186888","https://openalex.org/W1980401417","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W2542746790","https://openalex.org/W1428730622"],"abstract_inverted_index":{"For":[0],"segmenting":[1],"a":[2,6,23,64,80],"speech":[3],"database,":[4],"using":[5],"family":[7],"of":[8,14,67,82],"acoustic":[9],"models":[10,57],"provides":[11],"multiple":[12],"estimates":[13],"each":[15,61],"boundary":[16],"point.":[17],"This":[18,46],"is":[19],"more":[20],"robust":[21],"than":[22],"single":[24],"estimate":[25],"because":[26],"by":[27,79],"taking":[28],"consensus":[29],"values,":[30],"large":[31],"labeling":[32],"errors":[33],"are":[34,58],"less":[35],"prevalent":[36],"in":[37,51],"the":[38,43,73,77],"synthesis":[39],"catalog,":[40],"which":[41,52],"improves":[42],"resulting":[44],"voice.":[45],"paper":[47],"describes":[48],"HMM-based":[49],"segmentation":[50],"up":[53],"to":[54,60,84],"500":[55],"related":[56],"applied":[59],"wavefile.":[62],"In":[63],"listening":[65],"test":[66],"twelve":[68],"utterances,":[69],"human":[70],"judges":[71],"preferred":[72],"proposed":[74],"technique":[75],"over":[76],"baseline":[78],"tally":[81],"6":[83],"2,":[85],"with":[86],"4":[87],"ties.":[88]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}