{"id":"https://openalex.org/W4406858823","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849198","title":"Acoustic model adaptation in noisy and reverberated scenarios using multi-task learned embeddings","display_name":"Acoustic model adaptation in noisy and reverberated scenarios using multi-task learned embeddings","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858823","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849198"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5076856926","display_name":"Aditya Raikar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Raikar","raw_affiliation_strings":["Cerence Services (India) LLP,Pune,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cerence Services (India) LLP,Pune,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003062385","display_name":"Meet Soni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meet Soni","raw_affiliation_strings":["Rakuten Institute of Technology,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103959037","display_name":"Ashish Panda","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Panda","raw_affiliation_strings":["TCS Research,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research,Mumbai,India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047383705","display_name":"Sunil Kumar Kopparapu","orcid":"https://orcid.org/0000-0002-0502-527X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunil Kumar Kopparapu","raw_affiliation_strings":["TCS Research,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research,Mumbai,India","institution_ids":["https://openalex.org/I55215948"]}]}],"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":0.27219249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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":0.942300021648407,"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/task","display_name":"Task (project management)","score":0.7303788661956787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.690114438533783},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6564178466796875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3585405945777893},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13372358679771423},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10369232296943665},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0632627010345459}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7303788661956787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690114438533783},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6564178466796875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3585405945777893},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13372358679771423},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10369232296943665},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0632627010345459},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1601124178","https://openalex.org/W2052666245","https://openalex.org/W2079623482","https://openalex.org/W2150769028","https://openalex.org/W2164240571","https://openalex.org/W2290318471","https://openalex.org/W2555915854","https://openalex.org/W2630683241","https://openalex.org/W2671186495","https://openalex.org/W2680548194","https://openalex.org/W2696967604","https://openalex.org/W2750418488","https://openalex.org/W2766177643","https://openalex.org/W2807627734","https://openalex.org/W2890964092","https://openalex.org/W2900200882","https://openalex.org/W2901243971","https://openalex.org/W2936774411","https://openalex.org/W2962824709","https://openalex.org/W2963266252","https://openalex.org/W2972963519","https://openalex.org/W2973036346","https://openalex.org/W3007327651","https://openalex.org/W3198024420","https://openalex.org/W6631362777","https://openalex.org/W6748227048","https://openalex.org/W6844864630"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Distortions,":[0],"such":[1,66],"as":[2,67,108,110],"revebererations":[3],"and":[4,69,98],"background":[5],"noise":[6,104],"in":[7,33,96],"an":[8],"acoustic":[9,27,93],"environment":[10],"pose":[11],"a":[12,55],"significant":[13,120],"challenge":[14],"for":[15,49,75,89],"large-scale":[16],"Automatic":[17],"Speech":[18],"Recognition":[19],"(ASR)":[20],"systems.":[21],"In":[22],"this":[23,39,117],"paper":[24,79],"we":[25],"explore":[26],"model":[28,94],"adaption,":[29],"to":[30,37,46],"be":[31],"used":[32,74,124],"conjuction":[34],"with":[35,126],"multi-conditioning,":[36],"address":[38],"challenge.":[40],"Recently,":[41],"it":[42],"has":[43],"been":[44,73],"standard":[45],"use":[47,82],"i-vectors":[48],"Acoustic":[50],"Model":[51],"(AM)":[52],"adaptation.":[53,77],"With":[54],"varying":[56],"degree":[57],"of":[58,83],"success,":[59],"Single":[60],"Task":[61,85],"Learned":[62,86],"(STL)":[63],"neural":[64],"embeddings":[65,88],"x-vector":[68],"r-vector,":[70],"have":[71],"also":[72],"AM":[76],"This":[78],"proposes":[80],"the":[81,127],"Multi":[84],"(MTL)":[87],"large":[90],"vocabulary":[91],"hybrid":[92],"adaptation":[95],"noisy":[97],"reverberant":[99],"environments.":[100],"Our":[101],"experiments":[102],"on":[103],"added":[105],"Librispeech":[106],"database":[107,114],"well":[109],"real":[111],"reverberated":[112],"HRRE":[113],"show":[115],"that":[116],"approach":[118],"provides":[119],"performance":[121],"gain":[122],"when":[123],"along":[125],"traditional":[128],"i-vectors.":[129]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}