{"id":"https://openalex.org/W4224930731","doi":"https://doi.org/10.1109/icassp43922.2022.9746582","title":"Phone-Informed Refinement of Synthesized Mel Spectrogram for Data Augmentation in Speech Recognition","display_name":"Phone-Informed Refinement of Synthesized Mel Spectrogram for Data Augmentation in Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224930731","doi":"https://doi.org/10.1109/icassp43922.2022.9746582"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746582","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5103835523","display_name":"Sei Ueno","orcid":"https://orcid.org/0000-0002-2255-3154"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sei Ueno","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8572","last_page":"8576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9983999729156494,"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/spectrogram","display_name":"Spectrogram","score":0.9666801691055298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686000466346741},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7364261746406555},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6950498819351196},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6446009874343872},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5908128619194031},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4746447205543518},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.45017361640930176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3729594349861145},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36060667037963867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3459703326225281}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9666801691055298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686000466346741},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7364261746406555},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6950498819351196},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6446009874343872},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5908128619194031},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4746447205543518},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.45017361640930176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3729594349861145},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36060667037963867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3459703326225281},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746582","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2251321385","https://openalex.org/W2408688265","https://openalex.org/W2471520273","https://openalex.org/W2577366047","https://openalex.org/W2892009249","https://openalex.org/W2903739847","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2940200615","https://openalex.org/W2946200149","https://openalex.org/W2963091184","https://openalex.org/W2963827914","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W3008480565","https://openalex.org/W3015280134","https://openalex.org/W3015449694","https://openalex.org/W3016185664","https://openalex.org/W3024464021","https://openalex.org/W3033411150","https://openalex.org/W3095687973","https://openalex.org/W3097777922","https://openalex.org/W3097828251","https://openalex.org/W3097890746","https://openalex.org/W3107298252","https://openalex.org/W3161296985","https://openalex.org/W3162244132","https://openalex.org/W3196869722","https://openalex.org/W3197294703","https://openalex.org/W3198836239","https://openalex.org/W6601563604","https://openalex.org/W6629717138","https://openalex.org/W6691770337","https://openalex.org/W6741807409","https://openalex.org/W6746700228","https://openalex.org/W6754299077","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6784809985"],"related_works":["https://openalex.org/W1840351222","https://openalex.org/W642007152","https://openalex.org/W4306399915","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"While":[0],"recent":[1],"end-to-end":[2],"automatic":[3],"speech":[4,167],"recognition":[5],"(ASR)":[6],"models":[7],"achieve":[8],"high":[9],"performance,":[10],"we":[11,109],"need":[12],"to":[13,25,28,45,49,80,89,135,163,168,210,214],"prepare":[14],"an":[15,157],"abundant":[16],"amount":[17,103,175],"of":[18,36,104,176,186,199],"training":[19,37,55],"data,":[20,38,69],"which":[21],"is":[22,86,181,189],"a":[23,29,64,74,81,101,111,172,204],"barrier":[24],"apply":[26],"them":[27],"specific":[30],"domain.":[31],"To":[32],"mitigate":[33],"the":[34,56,91,121,146,153,184,192,197,200],"lack":[35],"text-to-speech":[39],"(TTS)":[40],"systems":[41],"have":[42],"been":[43],"utilized":[44],"leverage":[46],"text-only":[47],"data":[48,53,177],"efficiently":[50],"generate":[51],"paired":[52],"for":[54,140,191],"ASR":[57],"model.":[58],"The":[59,84,123],"widely-used":[60],"procedure":[61],"first":[62],"generates":[63],"Mel":[65,82,117,129],"spectrogram":[66],"from":[67],"text":[68,133],"then":[70],"converts":[71,77],"it":[72,78,99],"into":[73],"waveform,":[75],"and":[76,95],"again":[79],"spectrogram.":[83],"vocoder":[85,154],"often":[87],"used":[88],"alleviate":[90],"difference":[92],"between":[93],"real":[94],"synthesized":[96],"speech,":[97],"but":[98,131],"requires":[100],"huge":[102],"run-time.":[105],"In":[106],"this":[107],"work,":[108],"propose":[110],"phone-informed":[112],"post-processing":[113],"network":[114,125,148,155],"that":[115,145],"refines":[116],"spectrograms":[118,130],"without":[119],"using":[120],"vocoder.":[122],"proposed":[124,147,201],"consumes":[126],"not":[127],"only":[128],"also":[132,182,195],"information":[134,139,188],"use":[136,185],"phone":[137,187],"sequence":[138],"refinement.":[141],"Experimental":[142],"evaluations":[143],"demonstrate":[144],"achieves":[149],"better":[150],"WERs":[151],"than":[152],"in":[156,171,203],"English":[158],"domain":[159,206],"adaptation":[160,207],"task":[161,208],"(LibriSpeech":[162],"TED-LIUM":[164],"2;":[165],"read":[166],"spontaneous":[169],"speech)":[170],"much":[173],"smaller":[174],"generation":[178],"time.":[179],"It":[180],"shown":[183],"critical":[190],"improvement.":[193],"We":[194],"confirm":[196],"effect":[198],"model":[202],"Japanese":[205],"(CSJ-SPS":[209],"CSJ-APS;":[211],"everyday":[212],"topic":[213],"academic":[215],"topic).":[216]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}