{"id":"https://openalex.org/W3190171050","doi":"https://doi.org/10.1109/waspaa52581.2021.9632708","title":"A Multi-Head Relevance Weighting Framework for Learning Raw Waveform Audio Representations","display_name":"A Multi-Head Relevance Weighting Framework for Learning Raw Waveform Audio Representations","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3190171050","doi":"https://doi.org/10.1109/waspaa52581.2021.9632708","mag":"3190171050"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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/A5013284232","display_name":"Debottam Dutta","orcid":"https://orcid.org/0009-0009-6763-4511"},"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":"Debottam Dutta","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science,Bangalore,560012"],"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science,Bangalore,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050546237","display_name":"Purvi Agrawal","orcid":"https://orcid.org/0000-0002-1165-8348"},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Purvi Agrawal","raw_affiliation_strings":["Microsoft India Development Center,Hyderabad,India","Microsoft India Development Center, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Microsoft India Development Center,Hyderabad,India","institution_ids":["https://openalex.org/I4210162141"]},{"raw_affiliation_string":"Microsoft India Development Center, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"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, Indian Institute of Science,Bangalore,560012"],"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science,Bangalore,560012","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013284232"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.14397953,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43603045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 2011 1447","issue":null,"first_page":"191","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.7587896585464478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401796579360962},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6278077363967896},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6263659000396729},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5748661160469055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5197310447692871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5196236968040466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45889711380004883},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.45479658246040344},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.45383313298225403},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43465086817741394},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3304401636123657},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2953624725341797},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17207291722297668},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16135597229003906},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09951215982437134},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08619552850723267}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7587896585464478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401796579360962},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6278077363967896},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6263659000396729},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5748661160469055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5197310447692871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5196236968040466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45889711380004883},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.45479658246040344},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.45383313298225403},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43465086817741394},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3304401636123657},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2953624725341797},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17207291722297668},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16135597229003906},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09951215982437134},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08619552850723267},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:71268","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.8399999737739563,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1542280630","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1969851134","https://openalex.org/W2025653905","https://openalex.org/W2038484192","https://openalex.org/W2150884987","https://openalex.org/W2163922914","https://openalex.org/W2317919972","https://openalex.org/W2408093180","https://openalex.org/W2626778328","https://openalex.org/W2756577849","https://openalex.org/W2765407302","https://openalex.org/W2883935097","https://openalex.org/W2901616798","https://openalex.org/W2919115771","https://openalex.org/W2936774411","https://openalex.org/W2939710050","https://openalex.org/W2942544643","https://openalex.org/W2950577311","https://openalex.org/W2952218014","https://openalex.org/W2962835968","https://openalex.org/W2962901777","https://openalex.org/W2963399829","https://openalex.org/W2964052309","https://openalex.org/W2970971581","https://openalex.org/W2972984069","https://openalex.org/W2973049979","https://openalex.org/W3005680577","https://openalex.org/W3015384913","https://openalex.org/W3015530480","https://openalex.org/W3034978746","https://openalex.org/W3095950035","https://openalex.org/W3096891716","https://openalex.org/W3097327166","https://openalex.org/W3099330747","https://openalex.org/W3124414150","https://openalex.org/W3159777930","https://openalex.org/W4287372095","https://openalex.org/W4295312788","https://openalex.org/W4295723153","https://openalex.org/W4385245566","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6739901393","https://openalex.org/W6752516136","https://openalex.org/W6756859573","https://openalex.org/W6766978945","https://openalex.org/W6774314701","https://openalex.org/W6789403026"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2793814466"],"abstract_inverted_index":{"In":[0,135],"this":[1],"work,":[2],"we":[3],"propose":[4],"a":[5,28,39,69,102],"multi-head":[6,53,163],"relevance":[7,54,64,96,164],"weighting":[8],"framework":[9,48],"to":[10,101],"learn":[11],"audio":[12,18,114],"representations":[13,98],"from":[14],"raw":[15],"waveforms.":[16],"The":[17,42,95],"waveform,":[19],"split":[20],"into":[21],"windows":[22],"of":[23,32,45,52,62,84,144,162],"short-duration,":[24],"are":[25,99,118],"processed":[26],"with":[27],"1-D":[29],"convolutional":[30],"layer":[31],"cosine":[33],"modulated":[34],"Gaussian":[35],"filters":[36],"acting":[37],"as":[38,68,126,128],"learnable":[40],"filterbank.":[41],"key":[43],"novelty":[44],"the":[46,50,56,63,85,90,106,113,121,129,138,150,156,160,169],"proposed":[47,139],"is":[49,66,109],"introduction":[51],"on":[55,120,168],"learnt":[57,88],"filterbank":[58,93],"representations.":[59,171],"Each":[60],"head":[61],"network":[65],"modelled":[67],"separate":[70],"sub-network.":[71],"These":[72],"heads":[73],"perform":[74],"representation":[75,87],"enhancement":[76],"by":[77,89],"generating":[78],"weight":[79],"masks":[80],"for":[81,112,149],"different":[82],"parts":[83],"time-frequency":[86],"parametric":[91],"acoustic":[92],"layer.":[94],"weighted":[97],"fed":[100],"neural":[103],"classifier":[104],"and":[105,146,152],"whole":[107],"system":[108],"trained":[110],"jointly":[111],"classification":[115],"objective.":[116],"Experiments":[117],"performed":[119],"DCASE2020":[122,151],"Task":[123],"1A":[124],"challenge":[125],"well":[127],"Urban":[130],"Sound":[131],"Classification":[132],"(USC)":[133],"tasks.":[134],"these":[136],"experiments,":[137],"approach":[140],"yields":[141],"relative":[142],"improvements":[143],"10":[145],"23":[147],"respectively":[148],"USC":[153],"datasets":[154],"over":[155],"mel-spectrogram":[157],"baseline.":[158],"Also,":[159],"analysis":[161],"weights":[165],"provides":[166],"insights":[167],"learned":[170],"\u00c2\u00a9":[172],"2021":[173],"IEEE.":[174]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}