{"id":"https://openalex.org/W2134202996","doi":"https://doi.org/10.1109/icassp.2014.6854069","title":"Automatic discovery of a phonetic inventory for unwritten languages for statistical speech synthesis","display_name":"Automatic discovery of a phonetic inventory for unwritten languages for statistical speech synthesis","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2134202996","doi":"https://doi.org/10.1109/icassp.2014.6854069","mag":"2134202996"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103376290","display_name":"Prasanna Kumar Muthukumar","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":true,"raw_author_name":"Prasanna Kumar Muthukumar","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","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":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103376290"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.8189,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94033234,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2594","last_page":"2598"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.9945999979972839,"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":0.8430857062339783},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6153404712677002},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5972087979316711},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5911849141120911},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5463595390319824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5381869077682495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5329911112785339},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5270845293998718},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4986274242401123},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4382782280445099},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11045193672180176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8430857062339783},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6153404712677002},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5972087979316711},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5911849141120911},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5463595390319824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381869077682495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5329911112785339},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5270845293998718},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4986274242401123},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4382782280445099},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11045193672180176},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W95152782","https://openalex.org/W202879582","https://openalex.org/W1490506669","https://openalex.org/W1560013842","https://openalex.org/W1966264494","https://openalex.org/W1981457580","https://openalex.org/W1986174057","https://openalex.org/W2116648050","https://openalex.org/W2128446656","https://openalex.org/W2150612204","https://openalex.org/W2296704011","https://openalex.org/W2397987315","https://openalex.org/W2401299519","https://openalex.org/W2404169761","https://openalex.org/W2551677481","https://openalex.org/W4389138872","https://openalex.org/W6602682705","https://openalex.org/W6603838645","https://openalex.org/W6608197479","https://openalex.org/W6697285287","https://openalex.org/W6730233244"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1,18],"systems":[2,19,136],"are":[3,28,144],"typically":[4],"built":[5,137],"with":[6,138],"speech":[7,97],"data":[8],"and":[9,54],"transcriptions.":[10],"In":[11,43],"this":[12,44,139],"paper,":[13,45],"we":[14,46],"try":[15],"to":[16,34,99,106],"build":[17],"when":[20],"no":[21],"transcriptions":[22],"or":[23],"knowledge":[24,39,56],"about":[25,40,57,116],"the":[26,41,58,96,108,126,129],"language":[27,83],"available.":[29],"It":[30],"is":[31,73,93,104,122],"usually":[32],"necessary":[33],"at":[35,60],"least":[36],"possess":[37],"phonetic":[38,55],"language.":[42],"propose":[47],"an":[48,80],"automated":[49],"way":[50],"of":[51,65,118,128,135],"obtaining":[52],"phones":[53,121],"corpus":[59,78,98],"hand":[61],"by":[62,124],"making":[63],"use":[64],"Articulatory":[66,70],"Features":[67],"(AFs).":[68],"An":[69],"Feature":[71],"predictor":[72],"trained":[74],"on":[75,95],"a":[76,85],"bootstrap":[77],"in":[79,131,141],"arbitrary":[81],"other":[82],"using":[84],"three-hidden":[86],"layer":[87],"neural":[88,91],"network.":[89],"This":[90],"network":[92],"run":[94],"extract":[100],"AFs.":[101],"Hierarchical":[102],"clustering":[103],"used":[105],"cluster":[107],"AFs":[109,130],"into":[110],"categories":[111],"i.e.":[112],"phones.":[113],"Phonetic":[114],"information":[115],"each":[117,132],"these":[119],"inferred":[120],"obtained":[123],"computing":[125],"mean":[127],"cluster.":[133],"Results":[134],"framework":[140],"multiple":[142],"languages":[143],"reported.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}