{"id":"https://openalex.org/W3131573695","doi":"https://doi.org/10.1109/icassp39728.2021.9414649","title":"Representation Learning for Speech Recognition Using Feedback Based Relevance Weighting","display_name":"Representation Learning for Speech Recognition Using Feedback Based Relevance Weighting","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3131573695","doi":"https://doi.org/10.1109/icassp39728.2021.9414649","mag":"3131573695"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.07390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050546237","display_name":"Purvi Agrawal","orcid":"https://orcid.org/0000-0002-1165-8348"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Purvi Agrawal","raw_affiliation_strings":["Electrical Engineering, Indian Institute of Science, Bangalore, India","Indian Institute of Science,Electrical Engineering,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science,Electrical Engineering,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Electrical Engineering, Indian Institute of Science, Bangalore, India","Indian Institute of Science,Electrical Engineering,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science,Electrical Engineering,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050546237"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02682324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"6883","last_page":"6887"},"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/weighting","display_name":"Weighting","score":0.8847848176956177},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7671245336532593},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6994972229003906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6910338997840881},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6431340575218201},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5630241632461548},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5398496985435486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.504764199256897},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.502453088760376},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49653202295303345},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4801199436187744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4639641046524048},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4402920603752136},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4245275557041168},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4235292673110962},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08336412906646729},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0714607834815979},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06851127743721008}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8847848176956177},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7671245336532593},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6994972229003906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6910338997840881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6431340575218201},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5630241632461548},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5398496985435486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.504764199256897},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.502453088760376},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49653202295303345},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4801199436187744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4639641046524048},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4402920603752136},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4245275557041168},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4235292673110962},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08336412906646729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0714607834815979},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06851127743721008},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.07390","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07390","pdf_url":"https://arxiv.org/pdf/2102.07390","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai::81734","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/81734/1/MPRA_paper_81734.pdf","source":{"id":"https://openalex.org/S4306401702","display_name":"Universitas Pasundan institutional repositories & scientific journals (Universitas Pasundan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210159629","host_organization_name":"Universitas Pasundan","host_organization_lineage":["https://openalex.org/I4210159629"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},{"id":"mag:3131573695","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.07390","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.07390","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.07390","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/xsky-cz78","is_oa":true,"landing_page_url":"https://doi.org/10.17023/xsky-cz78","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.07390","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07390","pdf_url":"https://arxiv.org/pdf/2102.07390","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W154677192","https://openalex.org/W1498436455","https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1550695516","https://openalex.org/W1836465849","https://openalex.org/W1969851134","https://openalex.org/W2016589492","https://openalex.org/W2096051479","https://openalex.org/W2114719288","https://openalex.org/W2151484683","https://openalex.org/W2187089797","https://openalex.org/W2289394825","https://openalex.org/W2394873997","https://openalex.org/W2398826216","https://openalex.org/W2400622930","https://openalex.org/W2408093180","https://openalex.org/W2502312327","https://openalex.org/W2566553956","https://openalex.org/W2749980185","https://openalex.org/W2901616798","https://openalex.org/W2942544643","https://openalex.org/W2950577311","https://openalex.org/W2963175699","https://openalex.org/W2964121744","https://openalex.org/W2972984069","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2978904488","https://openalex.org/W3095950035","https://openalex.org/W3096891716","https://openalex.org/W3097498134","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6638667902","https://openalex.org/W6678409544","https://openalex.org/W6712560600","https://openalex.org/W6724804524","https://openalex.org/W6756859573"],"related_works":["https://openalex.org/W2397728357","https://openalex.org/W2133115605","https://openalex.org/W769229040","https://openalex.org/W2119763131","https://openalex.org/W2995506319","https://openalex.org/W3080080512","https://openalex.org/W2006780816","https://openalex.org/W1505251852","https://openalex.org/W2532540590","https://openalex.org/W2945616452","https://openalex.org/W2789246472","https://openalex.org/W3040785659","https://openalex.org/W1850708014","https://openalex.org/W2758758971","https://openalex.org/W1991662498","https://openalex.org/W2218800624","https://openalex.org/W2405486865","https://openalex.org/W3162646409","https://openalex.org/W1869491686","https://openalex.org/W1972312031"],"abstract_inverted_index":{"In":[0,35,51],"this":[1],"work,":[2],"we":[3],"propose":[4],"an":[5],"acoustic":[6,24],"embedding":[7],"based":[8,122],"approach":[9,18,95],"for":[10,96],"representation":[11],"learning":[12,26],"in":[13],"speech":[14,100],"recognition.":[15],"The":[16,70,90],"proposed":[17,71,94],"involves":[19],"two":[20],"stages":[21],"comprising":[22],"of":[23,59,92,99,129],"filterbank":[25,33],"from":[27,63],"raw":[28,115],"waveform,":[29],"followed":[30],"by":[31],"modulation":[32],"learning.":[34],"each":[36],"stage,":[37],"a":[38,47],"relevance":[39,54,72],"weighting":[40,55,73],"operation":[41],"is":[42],"employed":[43],"that":[44],"acts":[45],"as":[46,68,118,120],"feature":[48,78],"selection":[49],"module.":[50],"particular,":[52],"the":[53,60,64,76,87,93,97,132],"network":[56],"receives":[57],"embeddings":[58],"model":[61],"outputs":[62],"previous":[65],"time":[66],"instants":[67],"feedback.":[69],"scheme":[74],"allows":[75],"respective":[77],"representations":[79,125],"to":[80,86],"be":[81],"adaptively":[82],"selected":[83],"before":[84],"propagation":[85],"higher":[88],"layers.":[89],"application":[91],"task":[98],"recognition":[101],"on":[102,114,123,135,140],"Aurora-4":[103,136],"and":[104,138],"CHiME-3":[105,141],"datasets":[106],"gives":[107],"significant":[108],"performance":[109],"improvements":[110],"over":[111,131],"baseline":[112,134],"systems":[113],"waveform":[116],"signal":[117],"well":[119],"those":[121],"mel":[124,133],"(average":[126],"relative":[127],"improvement":[128],"15%":[130],"dataset":[137],"7%":[139],"dataset).":[142]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}