{"id":"https://openalex.org/W3161728052","doi":"https://doi.org/10.1109/icassp39728.2021.9415014","title":"Phone Distribution Estimation for Low Resource Languages","display_name":"Phone Distribution Estimation for Low Resource Languages","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161728052","doi":"https://doi.org/10.1109/icassp39728.2021.9415014","mag":"3161728052"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"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":"Xinjian Li","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"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":"Juncheng Li","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102857591","display_name":"Jiali Yao","orcid":"https://orcid.org/0009-0009-9673-3658"},"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":"Jiali Yao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04920587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"7233","last_page":"7237"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.8207861185073853},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7934485673904419},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6631951332092285},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6508355140686035},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5670897364616394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4972698986530304},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.48623624444007874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47833916544914246},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4611852765083313},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4485786557197571},{"id":"https://openalex.org/keywords/phone-call","display_name":"Phone call","score":0.42332717776298523},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.41879045963287354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41877397894859314},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4105044901371002},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11720660328865051},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.07984045147895813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207861185073853},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7934485673904419},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6631951332092285},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6508355140686035},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5670897364616394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4972698986530304},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.48623624444007874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47833916544914246},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4611852765083313},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4485786557197571},{"id":"https://openalex.org/C2994270382","wikidata":"https://www.wikidata.org/wiki/Q2296401","display_name":"Phone call","level":3,"score":0.42332717776298523},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.41879045963287354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41877397894859314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4105044901371002},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11720660328865051},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.07984045147895813},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W142212369","https://openalex.org/W191801690","https://openalex.org/W1532325895","https://openalex.org/W2003268946","https://openalex.org/W2009086942","https://openalex.org/W2035720976","https://openalex.org/W2135869163","https://openalex.org/W2347145335","https://openalex.org/W2501982834","https://openalex.org/W2514457011","https://openalex.org/W2591927543","https://openalex.org/W2805993470","https://openalex.org/W2901997113","https://openalex.org/W2937197076","https://openalex.org/W2963211739","https://openalex.org/W2964281804","https://openalex.org/W2972581290","https://openalex.org/W2998284473","https://openalex.org/W3015877095","https://openalex.org/W3017568157","https://openalex.org/W4244434307","https://openalex.org/W4361809191","https://openalex.org/W6752124048","https://openalex.org/W6756197946","https://openalex.org/W6776110202"],"related_works":["https://openalex.org/W2143391185","https://openalex.org/W2956015772","https://openalex.org/W2422904993","https://openalex.org/W2630417593","https://openalex.org/W2034674725","https://openalex.org/W4390110512","https://openalex.org/W2121490163","https://openalex.org/W3125473344","https://openalex.org/W2495884615","https://openalex.org/W2125864879"],"abstract_inverted_index":{"Phones":[0],"are":[1,33],"critical":[2],"components":[3],"in":[4,16,111],"various":[5],"computational":[6],"linguistic":[7],"fields,":[8],"for":[9],"example,":[10],"phone":[11,26,65,77],"distributions":[12,27,66],"could":[13],"be":[14],"helpful":[15],"speech":[17,20],"recognition":[18,82],"and":[19,84,115],"synthesis.":[21],"Traditional":[22],"approaches":[23],"to":[24,63,86],"estimate":[25,64,75],"typically":[28],"involve":[29],"G2P":[30],"systems":[31],"which":[32],"either":[34],"manually":[35],"designed":[36],"by":[37,67,79,96],"linguists":[38],"or":[39],"trained":[40],"on":[41,49,102],"large":[42],"datasets.":[43],"These":[44],"prohibitive":[45],"requirements":[46],"make":[47],"research":[48],"low":[50],"resource":[51],"languages":[52,104],"extremely":[53],"challenging.":[54],"In":[55],"this":[56],"work,":[57],"we":[58,90],"propose":[59],"a":[60],"novel":[61],"approach":[62],"only":[68],"requiring":[69],"raw":[70],"audio":[71],"datasets:":[72],"We":[73],"first":[74],"the":[76,92,106],"ranks":[78],"combining":[80],"language-independent":[81],"results":[83,101],"Learning":[85],"Rank":[87],"results.":[88],"Next,":[89],"approximate":[91],"distribution":[93,116],"with":[94],"Expectation-Maximization":[95],"fitting":[97],"Yule":[98],"distribution.":[99],"The":[100],"7":[103],"show":[105],"joint-model":[107],"has":[108],"better":[109],"performance":[110],"both":[112],"ranking":[113],"estimation":[114,117],"tasks.":[118]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}