{"id":"https://openalex.org/W4206656904","doi":"https://doi.org/10.23919/eusipco54536.2021.9616171","title":"End-to-end speech recognition from raw speech: Multi time-frequency resolution CNN architecture for efficient representation learning","display_name":"End-to-end speech recognition from raw speech: Multi time-frequency resolution CNN architecture for efficient representation learning","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4206656904","doi":"https://doi.org/10.23919/eusipco54536.2021.9616171"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616171","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616171","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5024759703","display_name":"Dhanya Eledath","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dhanya Eledath","raw_affiliation_strings":["International Institute of Information Technology - Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology - Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091367224","display_name":"P. Inbarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P. Inbarajan","raw_affiliation_strings":["Samsung R&D Institute, Bangalore (SRIB), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, Bangalore (SRIB), Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002861557","display_name":"Anurag Biradar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anurag Biradar","raw_affiliation_strings":["Samsung R&D Institute, Bangalore (SRIB), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, Bangalore (SRIB), Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064791478","display_name":"Sathwick Mahadeva","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sathwick Mahadeva","raw_affiliation_strings":["Samsung R&D Institute, Bangalore (SRIB), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, Bangalore (SRIB), Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036811576","display_name":"V. Ramasubramanian","orcid":"https://orcid.org/0000-0002-0676-9174"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"V. Ramasubramanian","raw_affiliation_strings":["IIIT- Bangalore,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"IIIT- Bangalore,Bangalore,India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5024759703"],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52860348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"536","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7716488242149353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5958083868026733},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5919183492660522},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5716792345046997},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5588511228561401},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5522779822349548},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5143488645553589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4979090690612793},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.4899107813835144},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.44083479046821594},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.43044590950012207},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24036270380020142},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12148553133010864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11598286032676697},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07330900430679321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716488242149353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5958083868026733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5919183492660522},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5716792345046997},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5588511228561401},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5522779822349548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5143488645553589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4979090690612793},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.4899107813835144},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.44083479046821594},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.43044590950012207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24036270380020142},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12148553133010864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11598286032676697},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07330900430679321},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616171","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616171","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1666984270","https://openalex.org/W1995562189","https://openalex.org/W2097117768","https://openalex.org/W2147800946","https://openalex.org/W2163922914","https://openalex.org/W2529337537","https://openalex.org/W2593179621","https://openalex.org/W2593451766","https://openalex.org/W2618530766","https://openalex.org/W2794150026","https://openalex.org/W2901616798","https://openalex.org/W2962785008","https://openalex.org/W2962793908","https://openalex.org/W2963669405","https://openalex.org/W2964052309","https://openalex.org/W3015579786","https://openalex.org/W3082096666","https://openalex.org/W6674914833","https://openalex.org/W6734751391","https://openalex.org/W6756859573"],"related_works":["https://openalex.org/W2610189143","https://openalex.org/W2964954556","https://openalex.org/W3019910406","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W4390971171","https://openalex.org/W4385338604","https://openalex.org/W3081626085"],"abstract_inverted_index":{"We":[0,17,91,126],"propose":[1],"a":[2,103,128,143],"multi":[3,32,65,83,135,179,188],"time-frequency":[4],"(t-f)":[5],"resolution":[6,67],"CNN":[7,68],"architecture":[8,70,94,137,175],"for":[9,88],"end-to-end":[10],"speech":[11,15],"recognition":[12],"from":[13],"raw":[14],"waveform.":[16],"address":[18],"issues":[19],"related":[20],"to":[21,80],"the":[22,29,39,44,82,109,118,133,149,159,170,173,178,194],"nature":[23],"of":[24,31,43,120,132,172],"front-end":[25],"convolutional":[26,41,114,185],"kernels":[27,75,115],"and":[28,38,54,76,108,153,193],"kind":[30],"t-f":[33,66,84,136,180,189],"spectrographic":[34,85,190],"feature":[35,45,86,105,191],"maps":[36,46,87,192],"formed":[37],"back-end":[40,77,195],"processing":[42],"within":[47],"two":[48,96,140,165],"tasks,":[49],"namely,":[50],"frame-wise":[51,150],"phoneme":[52,62,161],"classification":[53,151],"an":[55],"encoder-decoder":[56],"(with":[57],"CTC-Attention":[58],"loss)":[59],"based":[60,106],"continuous":[61,160],"decoding.":[63],"Our":[64],"(MT-CNN)":[69],"works":[71],"with":[72,95,123],"unconstrained":[73,181],"learnt":[74],"2D-convolutional":[78],"layers":[79],"process":[81],"these":[89,139],"tasks.":[90],"contrast":[92],"this":[93],"other":[97],"variants":[98,141],"in":[99,117,148,158,176],"recent":[100],"work":[101],"-":[102,142],"multi-scale":[104],"system":[107],"SincNet":[110],"(which":[111],"uses":[112],"parameterized":[113],"constrained":[116],"form":[119],"Sinc":[121],"functions":[122],"learnable":[124],"bandwidths).":[125],"show":[127],"consistent":[129],"performance":[130,166],"gain":[131],"proposed":[134,174],"over":[138],"3-8%":[144],"accuracy":[145],"(absolute":[146,156],"gain)":[147,157],"task":[152],"3%":[154],"PER":[155],"decoding":[162],"task.":[163],"These":[164],"gains":[167],"together":[168],"establish":[169],"effectiveness":[171],"using":[177],"variable":[182],"length":[183],"1-D":[184],"kernels,":[186],"2-D":[187,196],"convolution":[197],"layers.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}