{"id":"https://openalex.org/W2138550762","doi":"https://doi.org/10.21437/interspeech.2005-609","title":"Phonetic transcription verification with generalized posterior probability","display_name":"Phonetic transcription verification with generalized posterior probability","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W2138550762","doi":"https://doi.org/10.21437/interspeech.2005-609","mag":"2138550762"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-609","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104229610","display_name":"Min Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Chu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103536580","display_name":"Zhigang Cao","orcid":"https://orcid.org/0009-0006-7849-5885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhigang Cao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100436501"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3875,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94459673,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1949","last_page":"1952"},"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":0.9986000061035156,"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":0.9878000020980835,"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":0.7582269906997681},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6472636461257935},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.6269562840461731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6177880764007568},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.5395758152008057},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.525956392288208},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5121383666992188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4310351610183716},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4239840805530548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40949636697769165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1742609143257141},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.07797491550445557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582269906997681},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6472636461257935},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.6269562840461731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6177880764007568},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5395758152008057},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.525956392288208},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5121383666992188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4310351610183716},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4239840805530548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40949636697769165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1742609143257141},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.07797491550445557},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2005-609","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W180253589","https://openalex.org/W203263755","https://openalex.org/W854561988","https://openalex.org/W1515452908","https://openalex.org/W2115153515","https://openalex.org/W2134659216"],"related_works":["https://openalex.org/W2621258238","https://openalex.org/W2132470403","https://openalex.org/W2745284343","https://openalex.org/W2155576284","https://openalex.org/W2795856091","https://openalex.org/W2183463807","https://openalex.org/W175816486","https://openalex.org/W4388911376","https://openalex.org/W2382781231","https://openalex.org/W4388878702"],"abstract_inverted_index":{"Accurate":[0],"phonetic":[1,33,88],"transcription":[2,89],"is":[3,61,81,107,115],"critical":[4],"to":[5,17,29,83],"high":[6],"quality":[7],"concatenation":[8],"based":[9,63],"text-to-speech":[10],"synthesis.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15],"propose":[16],"use":[18],"generalized":[19],"syllable":[20,66],"posterior":[21],"probability":[22],"(GSPP)":[23],"as":[24,36],"a":[25,56,65,70,119],"statistical":[26],"confidence":[27],"measure":[28],"verify":[30],"errors":[31,47],"in":[32,43,48,55,86,132],"transcriptions,":[34],"such":[35],"reading":[37],"errors,":[38],"inadequate":[39],"alternatives":[40],"of":[41,95,126],"pronunciations":[42],"the":[44,78,111,123],"lexicon,":[45],"letter-to-sound":[46],"transcribing":[49],"out-of-vocabulary":[50],"words,":[51],"idiosyncratic":[52],"pronunciations,":[53],"etc.":[54],"TTS":[57],"speech":[58],"database.":[59],"GSPP":[60,80,112],"computed":[62],"upon":[64],"graph":[67],"generated":[68],"by":[69],"recognition":[71],"decoder.":[72],"Testing":[73],"on":[74,101],"two":[75,102],"data":[76],"sets,":[77,104],"proposed":[79],"shown":[82],"be":[84],"effective":[85],"locating":[87],"errors.":[90],"Equal":[91],"error":[92],"rates":[93],"(EERs)":[94],"8.2%":[96],"and":[97],"8.4%,":[98],"are":[99],"obtained":[100],"testing":[103],"respectively.":[105],"It":[106],"also":[108],"found":[109],"that":[110],"verification":[113],"performance":[114],"fairly":[116],"stable":[117],"over":[118],"wide":[120],"range":[121],"around":[122],"optimal":[124],"value":[125],"acoustic":[127],"model":[128],"exponential":[129],"weight":[130],"used":[131],"computing":[133],"GSPP.":[134]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
