{"id":"https://openalex.org/W3095950035","doi":"https://doi.org/10.1109/taslp.2020.3030489","title":"Interpretable Representation Learning for Speech and Audio Signals Based on Relevance Weighting","display_name":"Interpretable Representation Learning for Speech and Audio Signals Based on Relevance Weighting","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3095950035","doi":"https://doi.org/10.1109/taslp.2020.3030489","mag":"3095950035"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3030489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030489","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"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, Indian Institute of Science, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0002-1165-8348","affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":null,"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, Indian Institute of Science, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0002-5779-9066","affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore, 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":1.7607,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88311566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"2823","last_page":"2836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3319999873638153,"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":0.3319999873638153,"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":0.23280000686645508,"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":0.03530000150203705,"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/relevance","display_name":"Relevance (law)","score":0.7994999885559082},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7390999794006348},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5896999835968018},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4316999912261963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4212999939918518},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42080000042915344}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7994999885559082},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7390999794006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7321000099182129},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.605400025844574},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5504000186920166},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4316999912261963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.34130001068115234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.3030489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030489","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:eprints.iisc.ac.in:67438","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":"Journal Article"},{"id":"pmh:oai:arXiv.org:2011.02136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02136","pdf_url":"https://arxiv.org/pdf/2011.02136","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:2011.02136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02136","pdf_url":"https://arxiv.org/pdf/2011.02136","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":52,"referenced_works":["https://openalex.org/W154677192","https://openalex.org/W1498436455","https://openalex.org/W1542280630","https://openalex.org/W1969851134","https://openalex.org/W2017399882","https://openalex.org/W2025192094","https://openalex.org/W2025653905","https://openalex.org/W2038484192","https://openalex.org/W2043909051","https://openalex.org/W2046516274","https://openalex.org/W2059291967","https://openalex.org/W2096051479","https://openalex.org/W2107223151","https://openalex.org/W2114719288","https://openalex.org/W2116307430","https://openalex.org/W2130426352","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2150884987","https://openalex.org/W2163922914","https://openalex.org/W2289394825","https://openalex.org/W2394873997","https://openalex.org/W2408093180","https://openalex.org/W2421218773","https://openalex.org/W2529337537","https://openalex.org/W2566553956","https://openalex.org/W2658929981","https://openalex.org/W2749980185","https://openalex.org/W2756577849","https://openalex.org/W2791981959","https://openalex.org/W2796485741","https://openalex.org/W2889087444","https://openalex.org/W2939776061","https://openalex.org/W2942544643","https://openalex.org/W2962901777","https://openalex.org/W2972984069","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2973181078","https://openalex.org/W2978904488","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6636510571","https://openalex.org/W6638667902","https://openalex.org/W6678409544","https://openalex.org/W6712560600","https://openalex.org/W6713160670","https://openalex.org/W6724804524","https://openalex.org/W6732520560","https://openalex.org/W6735377749","https://openalex.org/W6739901393","https://openalex.org/W6756859573"],"related_works":[],"abstract_inverted_index":{"The":[0,42,106,138],"learning":[1,102,141],"of":[2,30,38,55,65,68,111,149,159,191],"interpretable":[3],"representations":[4,33],"from":[5],"raw":[6,76],"data":[7,14],"presents":[8],"significant":[9],"challenges":[10],"for":[11,121,146],"time":[12],"series":[13],"like":[15],"speech.":[16],"In":[17,179],"this":[18],"work,":[19],"we":[20],"propose":[21],"a":[22,48,69,122],"relevance":[23,43,59,87,91,104,112,161,170,192],"weighting":[24,44,193],"scheme":[25],"that":[26,51,168,188],"allows":[27],"the":[28,31,35,39,53,63,95,132,147,153,160,165,169,175,189,195,200],"interpretation":[29],"speech":[32,77,123,130,181],"during":[34],"forward":[36],"propagation":[37],"model":[40,73,109,166],"itself.":[41],"is":[45,119,143],"achieved":[46],"using":[47],"sub-network":[49,92],"approach":[50],"performs":[52,99],"task":[54,125,148],"feature":[56],"selection.":[57],"A":[58,89,156],"sub-network,":[60],"applied":[61,93,145],"on":[62,75,94,126],"output":[64],"first":[66],"layer":[67,85,98],"convolutional":[70,97,114],"neural":[71,196],"network":[72,197],"operating":[74],"signals,":[78],"acts":[79],"as":[80],"an":[81],"acoustic":[82,108],"filterbank":[83,101],"(FB)":[84],"with":[86,103],"weighting.":[88,105],"similar":[90],"second":[96],"modulation":[100],"full":[107],"consisting":[110],"sub-networks,":[113],"layers":[115,118],"and":[116,128,135,183],"feed-forward":[117],"trained":[120],"recognition":[124,182],"noisy":[127],"reverberant":[129],"in":[131,152,194],"Aurora-4,":[133],"CHiME-3":[134],"VOiCES":[136],"datasets.":[137],"proposed":[139],"representation":[140],"framework":[142],"also":[144],"sound":[150,184],"classification":[151,185],"UrbanSound8K":[154],"dataset.":[155],"detailed":[157],"analysis":[158],"weights":[162,171],"learned":[163],"by":[164],"reveals":[167],"capture":[172],"information":[173],"regarding":[174],"underlying":[176],"speech/audio":[177],"content.":[178],"addition,":[180],"experiments":[186],"reveal":[187],"incorporation":[190],"architecture":[198],"improves":[199],"performance":[201],"significantly.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2020-11-09T00:00:00"}