{"id":"https://openalex.org/W97413234","doi":"https://doi.org/10.21437/eurospeech.2003-127","title":"Evaluating and correcting phoneme segmentation for unit selection synthesis","display_name":"Evaluating and correcting phoneme segmentation for unit selection synthesis","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W97413234","doi":"https://doi.org/10.21437/eurospeech.2003-127","mag":"97413234"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-127","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Kominek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089589204","display_name":"Christina L. Bennett","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christina L. Bennett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan W. Black","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2628,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.92618778,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9976999759674072,"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":0.8768386840820312},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8354265093803406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.814061164855957},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7036341428756714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6353026628494263},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6078795790672302},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5893032550811768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5628693103790283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4907720983028412},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41723042726516724}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8768386840820312},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8354265093803406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814061164855957},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7036341428756714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6353026628494263},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6078795790672302},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5893032550811768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5628693103790283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4907720983028412},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41723042726516724}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-127","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2142401923","https://openalex.org/W2155368638"],"related_works":["https://openalex.org/W2419138286","https://openalex.org/W2347413598","https://openalex.org/W2507549656","https://openalex.org/W2330863229","https://openalex.org/W2050318184","https://openalex.org/W101156158","https://openalex.org/W2182848507","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2387825067"],"abstract_inverted_index":{"As":[0],"part":[1],"of":[2,22,47,65],"improved":[3],"support":[4],"for":[5,19],"building":[6],"unit":[7],"selection":[8],"voices,":[9],"the":[10,48],"Festival":[11],"speech":[12],"synthesis":[13],"system":[14],"now":[15],"includes":[16],"two":[17,26],"algorithms":[18],"automatic":[20],"labeling":[21,57],"wavefile":[23],"data.":[24],"The":[25],"methods":[27,70],"are":[28],"based":[29],"on":[30],"dynamic":[31],"time":[32],"warping":[33],"and":[34],"HMM-based":[35],"acoustic":[36],"modeling.":[37],"Our":[38],"experiments":[39],"show":[40],"that":[41],"DTW":[42],"is":[43,51],"more":[44,53],"accurate":[45],"70%":[46],"time,":[49],"but":[50],"also":[52],"prone":[54],"to":[55,78],"gross":[56],"errors.":[58],"HMM":[59],"modeling":[60],"exhibits":[61],"a":[62],"systematic":[63],"bias":[64],"15":[66],"ms.":[67],"Combining":[68],"both":[69],"directs":[71],"human":[72],"labelers":[73],"towards":[74],"data":[75],"most":[76],"likely":[77],"be":[79],"problematic.":[80]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}