{"id":"https://openalex.org/W4406461956","doi":"https://doi.org/10.1109/slt61566.2024.10832262","title":"Enhanced ASR FOR Stuttering Speech: Combining Adversarial and Signal-Based Data Augmentation","display_name":"Enhanced ASR FOR Stuttering Speech: Combining Adversarial and Signal-Based Data Augmentation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461956","doi":"https://doi.org/10.1109/slt61566.2024.10832262"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/A5113335993","display_name":"Shangkun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangkun Huang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024748224","display_name":"Dejun Zhang","orcid":"https://orcid.org/0000-0003-0951-9637"},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejun Zhang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727973","display_name":"Jing Deng","orcid":"https://orcid.org/0000-0003-4032-0482"},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Deng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056442083","display_name":"Rong Zheng","orcid":"https://orcid.org/0000-0003-4070-075X"},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Zheng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22220441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/speech-recognition","display_name":"Speech recognition","score":0.7606390118598938},{"id":"https://openalex.org/keywords/stuttering","display_name":"Stuttering","score":0.7393183708190918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341976761817932},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6927105784416199},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5174996852874756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3161490559577942},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.1411253809928894},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.057627975940704346}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7606390118598938},{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.7393183708190918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341976761817932},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6927105784416199},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5174996852874756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3161490559577942},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.1411253809928894},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.057627975940704346},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1989674786","https://openalex.org/W2168510624","https://openalex.org/W2407080277","https://openalex.org/W2696967604","https://openalex.org/W2791890919","https://openalex.org/W2913851961","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2963418739","https://openalex.org/W2963729456","https://openalex.org/W3015338123","https://openalex.org/W3095123370","https://openalex.org/W3161639065","https://openalex.org/W3163725792","https://openalex.org/W3197142850","https://openalex.org/W3197150384","https://openalex.org/W3198218550","https://openalex.org/W3198806843","https://openalex.org/W3207399576","https://openalex.org/W4200212915","https://openalex.org/W4221147660","https://openalex.org/W4281736089","https://openalex.org/W4309397917","https://openalex.org/W4319862255","https://openalex.org/W4320013936","https://openalex.org/W4366547420","https://openalex.org/W4366549322","https://openalex.org/W4379259581","https://openalex.org/W4385822966","https://openalex.org/W4387682382","https://openalex.org/W4388483000","https://openalex.org/W4392902590","https://openalex.org/W4392909075","https://openalex.org/W4401609106","https://openalex.org/W4402111964","https://openalex.org/W6810467415","https://openalex.org/W6838843145","https://openalex.org/W6845912186","https://openalex.org/W6853165267"],"related_works":["https://openalex.org/W2348937403","https://openalex.org/W2088087094","https://openalex.org/W2606084965","https://openalex.org/W604959964","https://openalex.org/W2043322848","https://openalex.org/W1483627603","https://openalex.org/W2103044274","https://openalex.org/W2163543546","https://openalex.org/W2036832189","https://openalex.org/W1877441159"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,63],"submission":[4],"to":[5,51,61],"the":[6,87,99,107],"SLT2024":[7],"StutteringSpeech":[8,88],"Challenge,":[9],"focusing":[10],"on":[11],"augmenting":[12],"stuttering":[13,53],"data":[14,25],"using":[15],"straightforward":[16],"and":[17,23,32,40,102],"effective":[18],"techniques.":[19],"We":[20],"combined":[21],"adversarial":[22],"signal-based":[24],"augmentation":[26],"methods,":[27],"including":[28],"modifying":[29],"speech":[30,38,54,65],"rate":[31,82],"rhythm,":[33],"inserting":[34],"silence":[35],"segments,":[36,39],"repeating":[37],"applying":[41],"Generative":[42],"Adversarial":[43],"Network-based":[44],"(GAN-based)":[45],"perturbation.":[46],"These":[47],"techniques":[48],"enabled":[49],"us":[50],"generate":[52],"from":[55],"fluent":[56],"speech,":[57],"which":[58],"we":[59],"used":[60],"train":[62],"automatic":[64],"recognition":[66],"(ASR)":[67],"model,":[68],"enhancing":[69],"its":[70],"robustness":[71],"for":[72],"individuals":[73],"with":[74],"stuttering.":[75],"Our":[76],"system":[77],"achieved":[78],"a":[79,93],"character":[80],"error":[81],"(CER)":[83],"of":[84,96],"12.30%":[85],"in":[86,106],"Challenge":[89],"Track":[90],"2,":[91],"demonstrating":[92],"relative":[94],"improvement":[95],"35.87%":[97],"over":[98],"official":[100],"baseline":[101],"securing":[103],"first":[104],"place":[105],"competition.":[108]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
