{"id":"https://openalex.org/W3097498134","doi":"https://doi.org/10.21437/interspeech.2020-2301","title":"Robust Raw Waveform Speech Recognition Using Relevance Weighted Representations","display_name":"Robust Raw Waveform Speech Recognition Using Relevance Weighted Representations","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097498134","doi":"https://doi.org/10.21437/interspeech.2020-2301","mag":"3097498134"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.00721","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":false,"raw_author_name":"Purvi Agrawal","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Dept. of Electrical Engg., Indian Institute of Science, Bengaluru-560012, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Dept. of Electrical Engg., Indian Institute of Science, Bengaluru-560012, 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":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Dept. of Electrical Engg., Indian Institute of Science, Bengaluru-560012, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Dept. of Electrical Engg., Indian Institute of Science, Bengaluru-560012, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.2709,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65476345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1649","last_page":"1653"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.7429311275482178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7238946557044983},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6758116483688354},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5988527536392212},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5841875672340393},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4972560703754425},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4870453178882599},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4569022059440613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44444185495376587},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44031721353530884},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4266486167907715},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41967999935150146},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4138796329498291},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.39740458130836487},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.312307745218277}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7429311275482178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7238946557044983},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6758116483688354},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5988527536392212},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5841875672340393},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4972560703754425},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4870453178882599},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4569022059440613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44444185495376587},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44031721353530884},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4266486167907715},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41967999935150146},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4138796329498291},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.39740458130836487},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.312307745218277},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020-2301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:67642","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:arXiv.org:2011.00721","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.00721","pdf_url":"https://arxiv.org/pdf/2011.00721","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.00721","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.00721","pdf_url":"https://arxiv.org/pdf/2011.00721","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":[{"score":0.5,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W154677192","https://openalex.org/W1498436455","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1593114658","https://openalex.org/W1614298861","https://openalex.org/W1836465849","https://openalex.org/W1969851134","https://openalex.org/W2017399882","https://openalex.org/W2043909051","https://openalex.org/W2088137865","https://openalex.org/W2096051479","https://openalex.org/W2114719288","https://openalex.org/W2130426352","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2151484683","https://openalex.org/W2289394825","https://openalex.org/W2394873997","https://openalex.org/W2398826216","https://openalex.org/W2400622930","https://openalex.org/W2408093180","https://openalex.org/W2421218773","https://openalex.org/W2502312327","https://openalex.org/W2566553956","https://openalex.org/W2749980185","https://openalex.org/W2756577849","https://openalex.org/W2901616798","https://openalex.org/W2939776061","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/W4231307919","https://openalex.org/W4245923654"],"related_works":["https://openalex.org/W2186375278","https://openalex.org/W2114026179","https://openalex.org/W2108641942","https://openalex.org/W2556771176","https://openalex.org/W2640905660","https://openalex.org/W2402949781","https://openalex.org/W1955848339","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,46,131,140,163],"in":[2,23,27,116,155],"noisy":[3,134],"and":[4,135],"channel":[5],"distorted":[6],"scenarios":[7],"is":[8,55,68,91,126],"often":[9],"challenging":[10],"as":[11],"the":[12,21,24,28,71,94,103,113,117,150,156,161,174],"current":[13],"acoustic":[14,39,109],"modeling":[15,40],"schemes":[16],"are":[17],"not":[18],"adaptive":[19],"to":[20,107],"changes":[22],"signal":[25],"distribution":[26],"presence":[29],"of":[30,73,76,152,171],"noise.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"develop":[36],"a":[37,58,77,87,129],"novel":[38],"framework":[41],"for":[42,102,128],"noise":[43],"robust":[44],"speech":[45,84,130,139,162],"based":[47],"on":[48,70,82,93,133,142],"relevance":[49,53,66,89,100,114,153],"weighting":[50,54,154],"mechanism.":[51],"The":[52,99,124,138],"achieved":[56],"using":[57],"sub-network":[59,67,90],"approach":[60],"that":[61,149],"performs":[62],"feature":[63],"selection.":[64,123],"A":[65],"applied":[69,92],"output":[72],"first":[74,104],"layer":[75,97,105,119],"convolutional":[78,96],"network":[79,158],"model":[80,125],"operating":[81],"raw":[83],"signals":[85],"while":[86,112],"second":[88,95,118],"output.":[98],"weights":[101,115],"correspond":[106],"an":[108],"filterbank":[110],"selection":[111],"perform":[120],"modulation":[121],"filter":[122],"trained":[127],"task":[132],"reverberant":[136],"speech.":[137],"experiments":[141],"multiple":[143],"datasets":[144],"(Aurora-4,":[145],"CHiME-3,":[146],"VOiCES)":[147],"reveal":[148],"incorporation":[151],"neural":[157],"architecture":[159],"improves":[160],"word":[164],"error":[165],"rates":[166],"significantly":[167],"(average":[168],"relative":[169],"improvements":[170],"10":[172],"over":[173],"baseline":[175],"systems).":[176],"\u00c2\u00a9":[177],"2020":[178],"ISCA":[179]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}