{"id":"https://openalex.org/W4297841831","doi":"https://doi.org/10.21437/interspeech.2022-117","title":"pMCT: Patched Multi-Condition Training for Robust Speech Recognition","display_name":"pMCT: Patched Multi-Condition Training for Robust Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841831","doi":"https://doi.org/10.21437/interspeech.2022-117"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-117","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-117","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5060097629","display_name":"Pablo Peso Parada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Pablo Peso Parada","raw_affiliation_strings":["Samsung Research, UK"],"affiliations":[{"raw_affiliation_string":"Samsung Research, UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039797069","display_name":"Agnieszka Dobrowolska","orcid":"https://orcid.org/0000-0002-3647-5070"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Agnieszka Dobrowolska","raw_affiliation_strings":["Samsung Research, UK"],"affiliations":[{"raw_affiliation_string":"Samsung Research, UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104088631","display_name":"Karthikeyan Saravanan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Karthikeyan Saravanan","raw_affiliation_strings":["Samsung Research, UK"],"affiliations":[{"raw_affiliation_string":"Samsung Research, UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054882290","display_name":"Mete \u00d6zay","orcid":"https://orcid.org/0000-0002-7189-7260"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mete Ozay","raw_affiliation_strings":["Samsung Research, UK"],"affiliations":[{"raw_affiliation_string":"Samsung Research, UK","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060097629"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.7271,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71401638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3779","last_page":"3783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.995199978351593,"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":0.9221000075340271,"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":0.7640411257743835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6295164227485657},{"id":"https://openalex.org/keywords/patched","display_name":"Patched","score":0.5888687968254089},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45219358801841736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3855476975440979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32497847080230713},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.05766740441322327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640411257743835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6295164227485657},{"id":"https://openalex.org/C2777994357","wikidata":"https://www.wikidata.org/wiki/Q24781250","display_name":"Patched","level":4,"score":0.5888687968254089},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45219358801841736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3855476975440979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32497847080230713},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.05766740441322327},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62478195","wikidata":"https://www.wikidata.org/wiki/Q828130","display_name":"Signal transduction","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C88498014","wikidata":"https://www.wikidata.org/wiki/Q14859918","display_name":"Hedgehog signaling pathway","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-117","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-117","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1922655562","https://openalex.org/W1999846783","https://openalex.org/W2099621636","https://openalex.org/W2219249508","https://openalex.org/W2296434735","https://openalex.org/W2401819598","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2617258110","https://openalex.org/W2696967604","https://openalex.org/W2759921250","https://openalex.org/W2765407302","https://openalex.org/W2768188490","https://openalex.org/W2888493875","https://openalex.org/W2936774411","https://openalex.org/W2962909949","https://openalex.org/W2963040451","https://openalex.org/W2963693826","https://openalex.org/W2972816482","https://openalex.org/W3009168442","https://openalex.org/W3015995734","https://openalex.org/W3094833745","https://openalex.org/W3096017728","https://openalex.org/W3096976326","https://openalex.org/W3097777922","https://openalex.org/W3127929528","https://openalex.org/W3138296617","https://openalex.org/W3163839574","https://openalex.org/W3167533889","https://openalex.org/W3171952436","https://openalex.org/W3196843354","https://openalex.org/W3204494926","https://openalex.org/W4225325562","https://openalex.org/W4226052192","https://openalex.org/W4297853167","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W2893763841","https://openalex.org/W2163831990","https://openalex.org/W2368779261","https://openalex.org/W3003836766","https://openalex.org/W2794438528","https://openalex.org/W2378160586","https://openalex.org/W1978450727"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,75],"novel":[3],"Patched":[4],"Multi-Condition":[5,59],"Training":[6,60],"(pMCT)":[7],"method":[8],"for":[9],"robust":[10,64],"Automatic":[11],"Speech":[12],"Recognition":[13],"(ASR).pMCT":[14],"employs":[15],"Multi-condition":[16],"Audio":[17],"Modification":[18],"and":[19,32],"Patching":[20],"(MAMP)":[21],"via":[22],"mixing":[23],"patches":[24],"of":[25,40],"the":[26,51,70,84,94],"same":[27],"utterance":[28],"extracted":[29],"from":[30,82],"clean":[31],"distorted":[33],"speech.Training":[34],"using":[35,57,80],"patchmodified":[36],"signals":[37],"improves":[38],"robustness":[39],"models":[41],"in":[42],"noisy":[43,76],"reverberant":[44,77],"scenarios.Our":[45],"proposed":[46],"pMCT":[47,68,86],"is":[48,74],"evaluated":[49],"on":[50,63,69],"LibriSpeech":[52],"dataset":[53,72,78],"showing":[54],"improvement":[55],"over":[56],"vanilla":[58],"(MCT).For":[61],"analyses":[62],"ASR,":[65],"we":[66],"employed":[67],"VOiCES":[71],"which":[73],"created":[79],"utterances":[81],"LibriSpeech.In":[83],"analyses,":[85],"achieves":[87],"23.1%":[88],"relative":[89],"WER":[90],"reduction":[91],"compared":[92],"to":[93],"MCT.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}