{"id":"https://openalex.org/W3197553328","doi":"https://doi.org/10.21437/interspeech.2021-53","title":"Speech Acoustic Modelling Using Raw Source and Filter Components","display_name":"Speech Acoustic Modelling Using Raw Source and Filter Components","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197553328","doi":"https://doi.org/10.21437/interspeech.2021-53","mag":"3197553328"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-53","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-53","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/5e3003c0-576d-4a28-bb98-5cc8f15db76b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["Centre for Speech Technology Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":["Department of Engineering, King's College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6997,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76516527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"280"},"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":0.9993000030517578,"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":0.9970999956130981,"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":0.6805973649024963},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4878835678100586},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.474804550409317},{"id":"https://openalex.org/keywords/source-model","display_name":"Source model","score":0.4515397846698761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3752404451370239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805973649024963},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4878835678100586},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.474804550409317},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.4515397846698761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3752404451370239},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-53","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-53","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/5e3003c0-576d-4a28-bb98-5cc8f15db76b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/5e3003c0-576d-4a28-bb98-5cc8f15db76b","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Loweimi, E, Cvetkovic, Z, Bell, P & Renals, S 2021, Speech Acoustic Modelling using Raw Source and Filter Components. in Proceedings of Interspeech 2021. International Speech Communication Association, pp. 716-720, Interspeech 2021, Brno, Czech Republic, 30/08/21. https://doi.org/10.21437/Interspeech.2021-53","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/5e3003c0-576d-4a28-bb98-5cc8f15db76b","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2021/loweimi21_interspeech.html","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:repository@napier.ac.uk:3585837","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585837","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"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":"Presentation / Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/5e3003c0-576d-4a28-bb98-5cc8f15db76b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/5e3003c0-576d-4a28-bb98-5cc8f15db76b","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Loweimi, E, Cvetkovic, Z, Bell, P & Renals, S 2021, Speech Acoustic Modelling using Raw Source and Filter Components. in Proceedings of Interspeech 2021. International Speech Communication Association, pp. 716-720, Interspeech 2021, Brno, Czech Republic, 30/08/21. https://doi.org/10.21437/Interspeech.2021-53","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3297227137","display_name":null,"funder_award_id":"EP/R012180/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6167047368","display_name":null,"funder_award_id":"EP/R012067/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1536990986","https://openalex.org/W1966264494","https://openalex.org/W2069501481","https://openalex.org/W2081096848","https://openalex.org/W2090861223","https://openalex.org/W2100974241","https://openalex.org/W2129082420","https://openalex.org/W2151626637","https://openalex.org/W2156387975","https://openalex.org/W2240641835","https://openalex.org/W2401447047","https://openalex.org/W2404126548","https://openalex.org/W2746321128","https://openalex.org/W2798983173","https://openalex.org/W2805215415","https://openalex.org/W2899771611","https://openalex.org/W2964227577","https://openalex.org/W2973053574","https://openalex.org/W2990440871","https://openalex.org/W3094114204","https://openalex.org/W3163845842","https://openalex.org/W4236328885","https://openalex.org/W4245923654"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2778699561","https://openalex.org/W2995996972","https://openalex.org/W2312116756","https://openalex.org/W3128571556","https://openalex.org/W4304891817","https://openalex.org/W2374918184"],"abstract_inverted_index":{"Source-filter":[0],"modelling":[1],"is":[2,60],"among":[3,82],"the":[4,27,38,45,56,63,107,117,124,131,140],"fundamental":[5],"techniques":[6],"in":[7,151,160],"speech":[8],"processing":[9,86],"with":[10,146],"a":[11,91],"wide":[12],"range":[13],"of":[14,40,93,103,110,119],"applications.":[15],"In":[16,33],"acoustic":[17,42,74],"modelling,":[18],"features":[19],"such":[20,111],"as":[21,55],"MFCC":[22],"and":[23,48,65,96,114,122,135,155,162],"PLP":[24],"which":[25],"parametrise":[26],"filter":[28,47],"component":[29],"are":[30,76],"widely":[31],"employed.":[32],"this":[34],"paper,":[35],"we":[36,129],"investigate":[37,116],"efficacy":[39],"building":[41],"models":[43,75,121],"from":[44],"raw":[46,52],"source":[49],"components.":[50],"The":[51,143],"magnitude":[53],"spectrum,":[54],"primary":[57],"information":[58,68,112],"stream,":[59],"decomposed":[61],"into":[62],"excitation":[64],"vocal":[66],"tract":[67],"streams":[69],"via":[70,78,90],"cepstral":[71],"liftering.":[72],"Then,":[73],"built":[77],"multi-head":[79],"CNNs":[80],"which,":[81],"others,":[83],"allow":[84],"for":[85,139],"each":[87],"individual":[88],"stream":[89],"sequence":[92],"bespoke":[94],"transforms":[95],"fusing":[97],"them":[98],"at":[99],"an":[100],"optimal":[101,125,147],"level":[102],"abstraction.":[104],"We":[105],"discuss":[106],"possible":[108],"advantages":[109],"factorisation":[113],"recombination,":[115],"dynamics":[118],"these":[120],"explore":[123],"fusion":[126,148],"level.":[127],"Furthermore,":[128],"illustrate":[130],"CNN\u2019s":[132],"learned":[133],"filters":[134],"provide":[136],"some":[137],"interpretation":[138],"captured":[141],"patterns.":[142],"proposed":[144],"approach":[145],"scheme":[149],"results":[150],"up":[152],"to":[153],"14%":[154],"7%":[156],"relative":[157],"WER":[158],"reduction":[159],"WSJ":[161],"Aurora-4":[163],"tasks.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}