{"id":"https://openalex.org/W2293596383","doi":"https://doi.org/10.21437/interspeech.2013-307","title":"Text-to-speech alignment of long recordings using universal phone models","display_name":"Text-to-speech alignment of long recordings using universal phone models","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2293596383","doi":"https://doi.org/10.21437/interspeech.2013-307","mag":"2293596383"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5020460474","display_name":"Sarah Hoffmann","orcid":"https://orcid.org/0000-0001-9549-2594"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Sarah Hoffmann","raw_affiliation_strings":["ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111975528","display_name":"Beat Pfister","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Beat Pfister","raw_affiliation_strings":["ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020460474"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":4.3283,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94548296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1520","last_page":"1524"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8550769090652466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7277112007141113},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6983810663223267},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6981146335601807},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6007420420646667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5434510707855225},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.5427030324935913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5405614972114563},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5345854759216309},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5287681818008423},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4878823757171631},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.48774176836013794},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4834062159061432},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4760681986808777},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44234126806259155},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41301098465919495},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.30883416533470154},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.082692950963974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550769090652466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7277112007141113},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6983810663223267},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6981146335601807},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6007420420646667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5434510707855225},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.5427030324935913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5405614972114563},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5345854759216309},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5287681818008423},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4878823757171631},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.48774176836013794},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4834062159061432},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4760681986808777},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44234126806259155},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41301098465919495},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30883416533470154},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.082692950963974},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W28591292","https://openalex.org/W203760253","https://openalex.org/W222076935","https://openalex.org/W1517939602","https://openalex.org/W2015412875","https://openalex.org/W2054665642","https://openalex.org/W2090755665","https://openalex.org/W2098267481","https://openalex.org/W2123798005","https://openalex.org/W2130414229","https://openalex.org/W2145880678","https://openalex.org/W2250270880","https://openalex.org/W2619993508","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W97919259","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2157598242","https://openalex.org/W3151376046","https://openalex.org/W3089379469","https://openalex.org/W2014684632","https://openalex.org/W2903652364","https://openalex.org/W2147630093"],"abstract_inverted_index":{"Large":[0],"recordings":[1],"like":[2],"radio":[3],"broadcasts":[4],"or":[5],"audio":[6],"books":[7],"are":[8],"an":[9,21,36,69,85],"interesting":[10],"additional":[11],"resource":[12],"for":[13,40,76],"speech":[14,34,50,55,126,150],"research":[15],"but":[16,20],"often":[17],"have":[18],"nothing":[19],"orthographic":[22],"transcription":[23,131],"available":[24,75],"in":[25,144],"terms":[26],"of":[27,109],"annotation.":[28],"The":[29],"alignment":[30,90,118,139],"between":[31],"text":[32,124],"and":[33,57,62,125],"is":[35,45,119],"important":[37],"first":[38],"step":[39],"further":[41],"processing.":[42],"Conventionally,":[43],"this":[44,81],"done":[46],"by":[47,105],"using":[48,106],"automatic":[49],"recognition":[51,60],"(ASR)":[52],"on":[53,88],"the":[54,66,77,138],"corpus":[56],"then":[58],"aligning":[59],"result":[61],"transcription.":[63],"This":[64],"has":[65],"drawback":[67],"that":[68,104],"ASR":[70,136],"system":[71],"needs":[72],"to":[73,99,121,135],"be":[74,142],"target":[78],"language.":[79],"In":[80,133],"paper,":[82],"we":[83],"introduce":[84],"approach":[86],"based":[87],"forced":[89,117],"with":[91],"hidden":[92],"Markov":[93],"models":[94,112,140],"(HMM)":[95],"normally":[96],"applied":[97],"only":[98],"shorter":[100],"utterances.":[101],"We":[102],"show":[103],"a":[107,145],"set":[108],"generalized":[110],"phone":[111],"computed":[113],"over":[114],"phonetic":[115],"groups,":[116],"able":[120],"reliably":[122],"align":[123],"while":[127],"being":[128],"robust":[129],"against":[130],"errors.":[132],"contrast":[134],"methods,":[137],"can":[141],"used":[143],"language-independent":[146],"way.":[147],"Index":[148],"Terms:":[149],"corpora":[151,156],"annotation,":[152],"sentence":[153],"segmentation,":[154],"large":[155],"processing":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}