{"id":"https://openalex.org/W3015654635","doi":"https://doi.org/10.1109/icassp40776.2020.9053139","title":"Speaker Augmentation for Low Resource Speech Recognition","display_name":"Speaker Augmentation for Low Resource Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015654635","doi":"https://doi.org/10.1109/icassp40776.2020.9053139","mag":"3015654635"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053139","doi":"https://doi.org/10.1109/icassp40776.2020.9053139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053139","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W3015654635"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847","observed_orcids":["https://orcid.org/0000-0001-5329-0847"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826","observed_orcids":["https://orcid.org/0000-0002-7102-9826"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.1595,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.9019994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7719","last_page":"7723"},"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":0.0,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/low-resource-speech-recognition","display_name":"low-resource speech recognition","score":0.8479999899864197},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9200000166893005},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8799999952316284},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.7879999876022339},{"id":"https://openalex.org/keywords/specaugment","display_name":"SpecAugment","score":0.9580000042915344},{"id":"https://openalex.org/keywords/feature-augmentation","display_name":"feature augmentation","score":0.7400000095367432},{"id":"https://openalex.org/keywords/switchboard-corpus","display_name":"Switchboard corpus","score":0.45399999618530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998334169387817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7943019270896912},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7196563482284546},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6613079309463501},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5836898684501648},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4972260296344757},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.488071084022522},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45949816703796387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4277111291885376},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05535271763801575},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053139","doi":"https://doi.org/10.1109/icassp40776.2020.9053139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053139","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W2062164080","https://openalex.org/W2102113734","https://openalex.org/W2120847449","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2515737026","https://openalex.org/W2626778328","https://openalex.org/W2885185669","https://openalex.org/W2886769154","https://openalex.org/W2892009249","https://openalex.org/W2898727538","https://openalex.org/W2907262790","https://openalex.org/W2936774411","https://openalex.org/W2940200615","https://openalex.org/W2962691331","https://openalex.org/W2962699523","https://openalex.org/W2963796886","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2972818416","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3114896262","https://openalex.org/W3024464021","https://openalex.org/W4385822638","https://openalex.org/W3161294170","https://openalex.org/W4225943493","https://openalex.org/W3163839574","https://openalex.org/W2983434507","https://openalex.org/W4210327373","https://openalex.org/W4408345790","https://openalex.org/W4408352600"],"abstract_inverted_index":{"Text-to-speech":[0],"synthesis":[1],"(TTS)":[2],"has":[3],"been":[4],"used":[5],"as":[6,117],"a":[7,29,51,77,99,121],"data":[8,59,103,152],"augmentation":[9,54,104,107,114,134],"approach":[10,55],"for":[11,19],"automatic":[12],"speech":[13,86],"recognition":[14],"(ASR),":[15],"leveraging":[16],"additional":[17],"texts":[18],"ASR":[20],"training.":[21],"However,":[22],"in":[23,43],"low":[24],"resource":[25],"tasks,":[26],"usually":[27],"only":[28],"limited":[30],"number":[31],"of":[32,40,102,129],"speakers":[33,90],"are":[34],"available,":[35],"leading":[36],"to":[37,84,147,159],"the":[38,94,131,148,160],"lack":[39],"speaker":[41,53,62,74,106,133],"variations":[42],"synthetic":[44],"speech.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"novel":[52],"which":[56,81],"can":[57,108],"synthesize":[58,85],"with":[60,73,111,135,162],"sufficient":[61],"and":[63,154],"text":[64],"diversity.":[65],"Here,":[66],"an":[67],"end-to-end":[68],"TTS":[69,83],"system":[70,149,161],"is":[71],"trained":[72,95],"representations":[75],"from":[76,87,93],"variational":[78],"auto-encoder":[79],"(VAE),":[80],"enables":[82],"unseen":[88],"new":[89,100],"via":[91],"sampling":[92],"latent":[96],"distribution.":[97],"As":[98],"type":[101],"approach,":[105],"be":[109],"combined":[110],"traditional":[112],"feature":[113],"approaches,":[115],"such":[116],"SpecAugment.":[118,163],"Experiments":[119],"on":[120],"switchboard":[122],"task":[123],"show":[124],"that,":[125],"given":[126],"50":[127],"hours":[128],"data,":[130],"proposed":[132],"SpecAugment":[136],"significantly":[137],"reduces":[138],"word":[139],"error":[140],"rate":[141],"(WER)":[142],"by":[143],"30%":[144],"relative":[145,157],"compared":[146,158],"without":[150],"any":[151],"augmentation,":[153],"about":[155],"18%":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2020-04-17T00:00:00"}