{"id":"https://openalex.org/W1594082249","doi":"https://doi.org/10.21437/icslp.2002-88","title":"Automatic segmentation combining an HMM-based approach and spectral boundary correction","display_name":"Automatic segmentation combining an HMM-based approach and spectral boundary correction","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W1594082249","doi":"https://doi.org/10.21437/icslp.2002-88","mag":"1594082249"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-88","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-88","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5066280625","display_name":"Yeon-Jun Kim","orcid":"https://orcid.org/0000-0003-4732-2501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeon-Jun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028548414","display_name":"Alistair Conkie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alistair Conkie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.412,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.92487973,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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":0.9968000054359436,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9883000254631042,"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/T10320","display_name":"Neural Networks and Applications","score":0.9833999872207642,"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":0.7126209735870361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6971001029014587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6361990571022034},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6077511310577393},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5622553825378418},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5207980871200562},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5191230177879333},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4287394881248474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4068235456943512},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16343346238136292}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7126209735870361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6971001029014587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6361990571022034},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6077511310577393},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5622553825378418},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5207980871200562},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5191230177879333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4287394881248474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4068235456943512},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16343346238136292},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2002-88","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-88","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.1066","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.1066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/%7Ettsweb/tts/papers/2002_ICSLP/autoseg.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W95822077","https://openalex.org/W146439846","https://openalex.org/W1481105745","https://openalex.org/W1560013842","https://openalex.org/W2033010331"],"related_works":["https://openalex.org/W2517104666","https://openalex.org/W2005437358","https://openalex.org/W177166743","https://openalex.org/W1669643531","https://openalex.org/W2008656436","https://openalex.org/W2134924024","https://openalex.org/W2023558673","https://openalex.org/W2358941527","https://openalex.org/W2110230079","https://openalex.org/W1982826852"],"abstract_inverted_index":{"Currently,":[0],"AT&T":[1],"Labs":[2],"\u2019":[3],"Natural":[4],"Voices":[5],"multilingual":[6],"TTS":[7],"system":[8],"produces":[9],"high-quality":[10],"synthetic":[11,80,116,145],"speech":[12,16,39,117,120],"with":[13],"a":[14,28,95,111,124],"largescale":[15],"corpus":[17],"[1].":[18],"In":[19],"the":[20,53,79,83,136],"development":[21],"of":[22,115],"such":[23,63],"systems,":[24],"automatic":[25,36,55,99],"segmentation":[26,37,100],"constitutes":[27],"major":[29],"component":[30],"technology.":[31],"The":[32],"prevalent":[33],"approach":[34,51,97,127],"for":[35,85],"in":[38,78,89,118,141,144],"synthesis":[40],"is":[41,52,139],"Hidden":[42],"Markov":[43],"Model":[44],"(HMM)-":[45],"based.":[46],"Even":[47],"though":[48],"an":[49],"HMM-based":[50,126],"most":[54],"and":[56,69,108,128],"reliable,":[57],"there":[58],"are":[59],"still":[60],"several":[61],"limitations,":[62],"as":[64],"mismatches":[65],"between":[66],"hand-labeled":[67,86],"transcriptions":[68],"HMM":[70,90],"alignment":[71],"labels":[72],"which":[73,101],"can":[74],"lead":[75],"to":[76,98,104,109],"discontinuities":[77,143],"speech,":[81],"or":[82],"need":[84],"bootstrap":[87],"data":[88],"initialization.":[91],"This":[92],"paper":[93],"introduces":[94],"new":[96],"aims":[102],"both":[103],"minimize":[105],"human":[106],"intervention":[107],"achieve":[110],"higher":[112],"segmental":[113],"quality":[114],"unit-concatenative":[119],"synthesis,":[121],"by":[122],"combining":[123],"conventional":[125],"spectral":[129],"boundary":[130],"correction.":[131],"A":[132],"preference":[133],"test":[134],"demonstrates":[135],"proposed":[137],"method":[138],"effective":[140],"reducing":[142],"speech.":[146],"1.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}