{"id":"https://openalex.org/W4319783480","doi":"https://doi.org/10.1109/iscslp57327.2022.10038031","title":"Speaking style compensation on synthetic audio for robust keyword spotting","display_name":"Speaking style compensation on synthetic audio for robust keyword spotting","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319783480","doi":"https://doi.org/10.1109/iscslp57327.2022.10038031"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038031","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5074673170","display_name":"Houjun Huang","orcid":"https://orcid.org/0000-0003-0757-0949"},"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":"Houjun Huang","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence,AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence,AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058261576","display_name":"BYanmin Qian","orcid":null},"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":"BYanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence,AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence,AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, 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":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"448","last_page":"452"},"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":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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":0.8375540971755981},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.766327977180481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7521350979804993},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7111461162567139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49586614966392517},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4611220061779022},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4417981207370758},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38438552618026733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375540971755981},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.766327977180481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7521350979804993},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7111461162567139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49586614966392517},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4611220061779022},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4417981207370758},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38438552618026733},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038031","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2219249508","https://openalex.org/W2769912137","https://openalex.org/W2888641632","https://openalex.org/W2889048668","https://openalex.org/W2890964092","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2963091184","https://openalex.org/W2963242190","https://openalex.org/W2964243274","https://openalex.org/W2973226577","https://openalex.org/W3010925296","https://openalex.org/W3015399080","https://openalex.org/W3015503328","https://openalex.org/W3024869864","https://openalex.org/W3025581723","https://openalex.org/W3096408984","https://openalex.org/W3097018422","https://openalex.org/W3132711939","https://openalex.org/W3145003630","https://openalex.org/W3162508345","https://openalex.org/W3163150275","https://openalex.org/W3163152557","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6746451879","https://openalex.org/W6754473786","https://openalex.org/W6763832098","https://openalex.org/W6784740452"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4385352507","https://openalex.org/W4389912005","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W2388033618","https://openalex.org/W105599799","https://openalex.org/W1483316057"],"abstract_inverted_index":{"With":[0],"the":[1,44,121,125,145,155],"rise":[2],"of":[3,62,104,154],"intelligent":[4],"speech":[5],"processing":[6],"applications,":[7],"quickly":[8],"producing":[9],"keyword":[10,106],"spotting":[11],"(KWS)":[12],"models":[13],"with":[14,54,65,114],"low":[15],"resource":[16],"has":[17,27],"gained":[18],"particular":[19],"importance":[20],"in":[21,43,48],"recent":[22],"years.":[23],"Multi-speaker":[24],"text-to-speech":[25],"(TTS)":[26],"been":[28],"proved":[29],"to":[30,39,84,88,92,134],"be":[31,89],"an":[32],"effective":[33],"data":[34,57,107],"augmentation":[35,142],"technique":[36],"for":[37],"KWS":[38,51,146],"help":[40],"complement":[41],"inadequacies":[42],"training":[45],"data.":[46],"However,":[47],"previous":[49],"works,":[50],"system":[52],"built":[53],"TTS":[55,141],"augmented":[56],"couldn\u2019t":[58],"obtain":[59],"considerable":[60],"performance":[61],"that":[63,140],"trained":[64,113],"real":[66,115],"recordings":[67,117],"as":[68,120],"synthetic":[69,156],"speeches":[70,87],"could":[71],"not":[72],"fully":[73],"represent":[74],"target":[75],"speaker\u2019s":[76,94],"speaking":[77,95,152],"style.":[78],"This":[79],"work":[80],"focuses":[81],"on":[82,108],"how":[83],"make":[85],"synthesized":[86,105],"more":[90],"similar":[91],"reference":[93],"style":[96,153],"under":[97],"a":[98,109,160],"specific":[99],"metric.":[100],"Speaker":[101],"classification":[102],"accuracy":[103],"speaker":[110],"recognition":[111],"model":[112],"common":[116],"is":[118,132],"used":[119,133],"objective":[122],"metrics,":[123],"and":[124],"deep":[126],"complex":[127],"convolution":[128],"recurrent":[129],"network":[130],"(DCCRN)":[131],"optimize":[135],"it.":[136],"Experimental":[137],"results":[138],"show":[139],"helps":[143],"improve":[144],"system\u2019s":[147],"robustness.":[148],"Moreover,":[149],"by":[150],"compensating":[151],"data,":[157],"we":[158],"achieve":[159],"significant":[161],"further":[162],"improvement.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}