{"id":"https://openalex.org/W3015237657","doi":"https://doi.org/10.1109/icassp40776.2020.9054309","title":"Incremental Semi-Supervised Learning for Multi-Genre Speech Recognition","display_name":"Incremental Semi-Supervised Learning for Multi-Genre Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015237657","doi":"https://doi.org/10.1109/icassp40776.2020.9054309","mag":"3015237657"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054309","pdf_url":null,"source":null,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/downloads/papers/2020/Khonglah_ICASSP2020_2020.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076301534","display_name":"Banriskhem K. Khonglah","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Banriskhem Khonglah","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062740398","display_name":"Subhadeep Dey","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Subhadeep Dey","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060493881","display_name":"Jayadev Billa","orcid":"https://orcid.org/0000-0002-9365-0162"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayadev Billa","raw_affiliation_strings":["Information Sciences Institute, University of Southern, California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern, California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076301534"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":2.1944,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89981738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7419","last_page":"7423"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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":0.7733019590377808},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7162374258041382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5446987152099609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5261637568473816},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5110393762588501},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48941269516944885},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4499928057193756},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4247598648071289},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40285158157348633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34520334005355835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3320907950401306},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26921001076698303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13396182656288147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733019590377808},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7162374258041382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446987152099609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5261637568473816},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5110393762588501},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48941269516944885},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4499928057193756},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4247598648071289},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40285158157348633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34520334005355835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3320907950401306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26921001076698303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13396182656288147},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054309","pdf_url":null,"source":null,"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"},{"id":"pmh:oai:infoscience.epfl.ch:277106","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/168281","pdf_url":"http://publications.idiap.ch/downloads/papers/2020/Khonglah_ICASSP2020_2020.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:277106","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/168281","pdf_url":"http://publications.idiap.ch/downloads/papers/2020/Khonglah_ICASSP2020_2020.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015237657.pdf","grobid_xml":"https://content.openalex.org/works/W3015237657.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1892788530","https://openalex.org/W1965842648","https://openalex.org/W1975113979","https://openalex.org/W1993660824","https://openalex.org/W2012190582","https://openalex.org/W2079623482","https://openalex.org/W2085598899","https://openalex.org/W2110073835","https://openalex.org/W2124558353","https://openalex.org/W2147590749","https://openalex.org/W2402146185","https://openalex.org/W2802248956","https://openalex.org/W2888842383","https://openalex.org/W2888867175","https://openalex.org/W2889162046","https://openalex.org/W2911629330","https://openalex.org/W2937308178","https://openalex.org/W2950559196","https://openalex.org/W2962907457","https://openalex.org/W2963540920","https://openalex.org/W2972840640","https://openalex.org/W2973143291","https://openalex.org/W6631362777","https://openalex.org/W6681784473","https://openalex.org/W6712930963","https://openalex.org/W6758052375"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W2146197305","https://openalex.org/W2134950286","https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2168489430","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2584084702"],"abstract_inverted_index":{"In":[0,50],"this":[1,51],"work,":[2],"we":[3,53],"explore":[4],"a":[5,24,79],"data":[6,30,40,86,125],"scheduling":[7,115],"strategy":[8,116],"for":[9,13,45,76,88,110,128],"semi-supervised":[10],"learning":[11],"(SSL)":[12],"acoustic":[14,47,100,137],"modeling":[15],"in":[16,57,72,95,126,164],"automatic":[17],"speech":[18],"recognition.":[19],"The":[20,99],"conventional":[21],"approach":[22,56,121],"uses":[23],"seed":[25,108],"model":[26,48,101,109,138],"trained":[27],"with":[28],"supervised":[29],"to":[31,41,84,119,162],"automatically":[32],"recognize":[33],"the":[34,59,85,96,103,107,111,120,150],"entire":[35],"set":[36,61],"of":[37,160],"unlabeled":[38,124],"(auxiliary)":[39],"generate":[42],"new":[43,80],"labels":[44],"subsequent":[46],"training.":[49,129],"paper,":[52],"propose":[54],"an":[55,73],"which":[58],"unlabelled":[60],"is":[62,82,117],"divided":[63],"into":[64],"multiple":[65],"equal-sized":[66],"subsets.":[67],"These":[68],"subsets":[69],"are":[70,168],"processed":[71],"incremental":[74],"fashion:":[75],"each":[77],"iteration":[78,105],"subset":[81,94],"added":[83],"used":[87],"SSL,":[89],"starting":[90],"from":[91,102],"only":[92],"one":[93],"first":[97],"iteration.":[98],"previous":[104],"becomes":[106],"next":[112],"one.":[113],"This":[114],"compared":[118],"employing":[122],"all":[123],"one-shot":[127],"Experiments":[130],"using":[131],"lattice-free":[132],"maximum":[133],"mutual":[134],"information":[135],"based":[136],"training":[139],"on":[140,154],"Fisher":[141],"English":[142],"gives":[143],"80%":[144],"word":[145,165],"error":[146,166],"recovery":[147],"rate.":[148],"On":[149],"multi-genre":[151],"evaluation":[152],"sets":[153],"Lithuanian":[155],"and":[156],"Bulgarian":[157],"relative":[158],"improvements":[159],"up":[161],"17.2%":[163],"rate":[167],"observed.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}