{"id":"https://openalex.org/W3089432592","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206778","title":"Learning Filterbanks from Raw Waveform for Accent Classification","display_name":"Learning Filterbanks from Raw Waveform for Accent Classification","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089432592","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206778","mag":"3089432592"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/a95b94de-27ac-49be-97a5-0de52aa5bbaa","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068718894","display_name":"Rashmi Kethireddy","orcid":"https://orcid.org/0000-0002-3047-8158"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rashmi Kethireddy","raw_affiliation_strings":["Speech Processing Laboratory, IIIT-Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, IIIT-Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058673990","display_name":"Suryakanth V. Gangashetty","orcid":"https://orcid.org/0000-0001-6745-4363"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakanth V. Gangashetty","raw_affiliation_strings":["Speech Processing Laboratory, IIIT-Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, IIIT-Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068718894"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.6796,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.77086805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9991000294685364,"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":0.9988999962806702,"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/waveform","display_name":"Waveform","score":0.7762244343757629},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7016549706459045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5922845602035522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5840058922767639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49857282638549805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41640424728393555},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08668920397758484}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7762244343757629},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7016549706459045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5922845602035522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5840058922767639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49857282638549805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41640424728393555},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08668920397758484},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/47472","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/a95b94de-27ac-49be-97a5-0de52aa5bbaa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/47472","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/a95b94de-27ac-49be-97a5-0de52aa5bbaa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[{"id":"https://openalex.org/G6805937789","display_name":null,"funder_award_id":"NET-NOV2017","funder_id":"https://openalex.org/F4320320767","funder_display_name":"University Grants Commission"},{"id":"https://openalex.org/G8355436068","display_name":null,"funder_award_id":"India","funder_id":"https://openalex.org/F4320320767","funder_display_name":"University Grants Commission"}],"funders":[{"id":"https://openalex.org/F4320320767","display_name":"University Grants Commission","ror":"https://ror.org/04p800546"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W86944614","https://openalex.org/W191155385","https://openalex.org/W251439765","https://openalex.org/W1529116532","https://openalex.org/W1542280630","https://openalex.org/W1657486103","https://openalex.org/W1665214252","https://openalex.org/W1981320719","https://openalex.org/W1995562189","https://openalex.org/W2003573652","https://openalex.org/W2040357394","https://openalex.org/W2093231248","https://openalex.org/W2095705004","https://openalex.org/W2103212315","https://openalex.org/W2112796928","https://openalex.org/W2130721836","https://openalex.org/W2133803203","https://openalex.org/W2137498753","https://openalex.org/W2163605009","https://openalex.org/W2175013346","https://openalex.org/W2293441309","https://openalex.org/W2398826216","https://openalex.org/W2408093180","https://openalex.org/W2505434962","https://openalex.org/W2529337537","https://openalex.org/W2747743419","https://openalex.org/W2770454110","https://openalex.org/W2793012778","https://openalex.org/W2889494795","https://openalex.org/W2914465356","https://openalex.org/W2930753566","https://openalex.org/W2962901777","https://openalex.org/W2962922562","https://openalex.org/W2963071736","https://openalex.org/W2963691377","https://openalex.org/W2972455439","https://openalex.org/W2972967118","https://openalex.org/W2973037561","https://openalex.org/W4250135370","https://openalex.org/W6637242042","https://openalex.org/W6674330103","https://openalex.org/W6684191040","https://openalex.org/W6685610332","https://openalex.org/W6696997943","https://openalex.org/W6712560600"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W3003836766","https://openalex.org/W2893763841","https://openalex.org/W2163831990","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2378160586","https://openalex.org/W1978450727"],"abstract_inverted_index":{"Most":[0],"of":[1,35,65,75,112,137,155,171,179],"the":[2,16,21,41,49,73,96,107,135,152,160,177],"applications":[3],"in":[4,30,91,103,167],"speech":[5],"use":[6,62],"mel-frequency":[7],"spectral":[8],"coefficients":[9],"(MFSC)":[10],"as":[11,13,102],"features":[12,77,147],"they":[14],"match":[15],"human":[17],"perceptual":[18],"mechanism,":[19],"where":[20,48],"emphasis":[22,50],"is":[23,89,121],"given":[24],"to":[25,79,123,142],"vocal":[26,54],"tract":[27],"characteristics.":[28],"But":[29],"accent":[31,125,138],"classification,":[32],"mel-scale":[33],"distribution":[34,168],"filters":[36,161],"may":[37],"not":[38],"always":[39],"be":[40,52],"best":[42],"representations,":[43],"e.g.,":[44],"pitch":[45],"accented":[46],"languages":[47],"should":[51],"on":[53,145,151],"source":[55],"information":[56],"too.":[57],"Motivated":[58],"by":[59,105,148],"this,":[60],"we":[61,164],"end-to-end":[63],"classification":[64,139],"accents":[66],"directly":[67,131],"from":[68,132],"waveforms":[69],"which":[70],"will":[71],"reduce":[72],"effort":[74],"designing":[76],"specific":[78],"each":[80],"corpus.":[81,158],"The":[82,114],"convolution":[83],"neural":[84],"network":[85,116],"(CNN)":[86],"model":[87],"architecture":[88],"designed":[90],"such":[92],"a":[93],"way":[94],"that":[95,129],"initial":[97,119],"layers":[98,120],"exhibit":[99],"similar":[100],"operation":[101],"MFSC":[104],"initializing":[106,181],"weights":[108],"using":[109],"time":[110],"approximate":[111],"MFSC.":[113],"entire":[115],"along":[117],"with":[118],"trained":[122,144],"learn":[124],"classification.":[126],"We":[127,174],"observed":[128,165,176],"learning":[130],"waveform":[133],"improved":[134],"performance":[136],"when":[140],"compared":[141],"CNN":[143,182],"hand-engineered":[146],"10.94%":[149],"UAR":[150],"test":[153],"dataset":[154],"common":[156],"voice":[157],"Analyzing":[159],"after":[162],"learning,":[163],"changes":[166],"and":[169],"bandwidths":[170],"center":[172],"frequencies.":[173],"further":[175],"importance":[178],"appropriately":[180],"filters.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}