{"id":"https://openalex.org/W2938630833","doi":"https://doi.org/10.1109/icassp.2019.8682550","title":"Improving Human-computer Interaction in Low-resource Settings with Text-to-phonetic Data Augmentation","display_name":"Improving Human-computer Interaction in Low-resource Settings with Text-to-phonetic Data Augmentation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938630833","doi":"https://doi.org/10.1109/icassp.2019.8682550","mag":"2938630833"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5027836113","display_name":"Adam Stiff","orcid":"https://orcid.org/0000-0002-5158-8508"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Stiff","raw_affiliation_strings":["Department of Computer Science & Engineering, The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070013411","display_name":"Prashant Serai","orcid":"https://orcid.org/0000-0002-4672-4413"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Serai","raw_affiliation_strings":["Department of Computer Science & Engineering, The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Department of Computer Science & Engineering, The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7320","last_page":"7324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8401200175285339},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6334496736526489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5874150395393372},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5321822166442871},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5299438238143921},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5009639263153076},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.49852705001831055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43982794880867004},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42516303062438965},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4145750105381012},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37862467765808105},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32423165440559387},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29423001408576965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8401200175285339},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6334496736526489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5874150395393372},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5321822166442871},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5299438238143921},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5009639263153076},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.49852705001831055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43982794880867004},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42516303062438965},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4145750105381012},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37862467765808105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32423165440559387},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29423001408576965},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W28412257","https://openalex.org/W1832693441","https://openalex.org/W2110065044","https://openalex.org/W2116064496","https://openalex.org/W2153579005","https://openalex.org/W2164666834","https://openalex.org/W2251711535","https://openalex.org/W2581637843","https://openalex.org/W2756554273","https://openalex.org/W2936399153","https://openalex.org/W4294170691","https://openalex.org/W6600284362","https://openalex.org/W6682691769","https://openalex.org/W6691575401"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2037564206","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2971899271","https://openalex.org/W1972167985"],"abstract_inverted_index":{"Off-the-shelf":[0],"speech":[1,58,129],"recognition":[2],"systems":[3,14],"can":[4,19],"yield":[5],"useful":[6],"results":[7],"and":[8],"accelerate":[9],"application":[10],"development,":[11],"but":[12],"general-purpose":[13],"applied":[15],"to":[16,33,49,93,117,131],"specialized":[17],"domains":[18],"introduce":[20],"acoustically":[21],"small-but":[22],"semantically":[23,85],"catastrophic-errors.":[24],"Furthermore,":[25],"sufficient":[26],"audio":[27,65],"data":[28,74],"may":[29],"not":[30],"be":[31],"available":[32,70],"develop":[34],"custom":[35],"acoustic":[36,87],"models":[37],"for":[38,112],"niche":[39],"tasks.":[40],"To":[41],"address":[42],"these":[43],"problems,":[44],"we":[45],"propose":[46],"a":[47,107,124,132],"concept":[48],"improve":[50],"performance":[51],"in":[52,106],"text":[53,72],"classification":[54,133],"tasks":[55],"that":[56,80],"use":[57],"transcripts":[59,130],"as":[60],"input,":[61],"without":[62],"any":[63],"in-domain":[64],"data.":[66],"Our":[67],"method":[68,105],"augments":[69],"typewritten":[71],"training":[73],"with":[75],"inferred":[76],"phonetic":[77],"information":[78],"so":[79],"the":[81,97],"classifier":[82],"will":[83],"learn":[84],"important":[86],"regularities,":[88],"making":[89],"it":[90],"more":[91],"robust":[92],"transcription":[94],"errors":[95,120],"from":[96],"general":[98],"purpose":[99],"ASR.":[100],"We":[101],"successfully":[102],"pilot":[103],"our":[104],"speech-based":[108],"virtual":[109],"patient":[110],"used":[111],"medical":[113],"training,":[114],"recovering":[115],"up":[116],"62%":[118],"of":[119,128],"incurred":[121],"by":[122],"feeding":[123],"small":[125],"test":[126],"set":[127],"model":[134],"trained":[135],"on":[136],"typescript.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}