{"id":"https://openalex.org/W3163845842","doi":"https://doi.org/10.1109/icassp39728.2021.9413727","title":"Speech Acoustic Modelling from Raw Phase Spectrum","display_name":"Speech Acoustic Modelling from Raw Phase Spectrum","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163845842","doi":"https://doi.org/10.1109/icassp39728.2021.9413727","mag":"3163845842"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/fe86f347-5b7c-4808-a980-b789262d5388","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":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research (CSTR),UK","Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research (CSTR),UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":["King’s College London,Department of Engineering,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering,UK","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research (CSTR),UK","Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research (CSTR),UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research (CSTR),UK","Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research (CSTR),UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2594,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8353265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6738","last_page":"6742"},"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":0.9998000264167786,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215801477432251},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6333745718002319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5729131698608398},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.5357792377471924},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48168787360191345},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4292840361595154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3315808176994324},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12928664684295654},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1283080279827118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215801477432251},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6333745718002319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5729131698608398},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.5357792377471924},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48168787360191345},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4292840361595154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3315808176994324},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12928664684295654},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1283080279827118},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/3db63717-2584-423e-a641-81fb9f75db45","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85115098654&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Loweimi, E, Cvetkovic, Z, Bell, P & Renals, S 2021, 'Speech acoustic modelling from raw phase spectrum', ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2021-June, pp. 6738-6742. https://doi.org/10.1109/ICASSP39728.2021.9413727","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/fe86f347-5b7c-4808-a980-b789262d5388","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/fe86f347-5b7c-4808-a980-b789262d5388","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 From Raw Phase Spectrum. in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 6738-6742, 46th IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Ontario, Canada, 6/06/21. https://doi.org/10.1109/ICASSP39728.2021.9413727","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/fe86f347-5b7c-4808-a980-b789262d5388","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/fe86f347-5b7c-4808-a980-b789262d5388","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:3585849","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585849","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/fe86f347-5b7c-4808-a980-b789262d5388","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/fe86f347-5b7c-4808-a980-b789262d5388","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 From Raw Phase Spectrum. in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 6738-6742, 46th IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Ontario, Canada, 6/06/21. https://doi.org/10.1109/ICASSP39728.2021.9413727","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"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":33,"referenced_works":["https://openalex.org/W143947237","https://openalex.org/W1524333225","https://openalex.org/W1860981223","https://openalex.org/W1896470158","https://openalex.org/W1976761624","https://openalex.org/W2007115401","https://openalex.org/W2009562705","https://openalex.org/W2024490156","https://openalex.org/W2052043304","https://openalex.org/W2126597753","https://openalex.org/W2145212718","https://openalex.org/W2151484683","https://openalex.org/W2168709618","https://openalex.org/W2170787898","https://openalex.org/W2291877678","https://openalex.org/W2399785508","https://openalex.org/W2401447047","https://openalex.org/W2594170997","https://openalex.org/W2746013913","https://openalex.org/W2746321128","https://openalex.org/W2801848743","https://openalex.org/W2805215415","https://openalex.org/W2889160436","https://openalex.org/W2939497224","https://openalex.org/W2964227577","https://openalex.org/W3127686677","https://openalex.org/W6605853638","https://openalex.org/W6631362777","https://openalex.org/W6682194319","https://openalex.org/W6685463904","https://openalex.org/W6712794749","https://openalex.org/W6713058952","https://openalex.org/W6752308553"],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W2617269004","https://openalex.org/W35292311","https://openalex.org/W1748856376","https://openalex.org/W2803166627","https://openalex.org/W2046073792","https://openalex.org/W1591384192","https://openalex.org/W2099204336","https://openalex.org/W2067459736","https://openalex.org/W2105635394"],"abstract_inverted_index":{"Magnitude":[0],"spectrum-based":[1],"features":[2],"are":[3],"the":[4,23,31,40,43,54,57,68,74,81,96,126,139],"most":[5],"widely":[6],"employed":[7],"front-ends":[8],"for":[9,62,98,107,113],"acoustic":[10,28,63],"modelling":[11,29],"in":[12,138],"automatic":[13],"speech":[14,108],"recognition":[15],"(ASR)":[16],"systems.":[17],"In":[18,36],"this":[19],"paper,":[20],"we":[21,38,66],"investigate":[22,89],"possibility":[24],"and":[25,47,59,77,88,130],"efficacy":[26],"of":[27,42,56,70,73,80],"using":[30,85],"raw":[32,44,82],"short-time":[33],"phase":[34,49,55,83,115],"spectrum.":[35],"particular,":[37],"study":[39],"usefulness":[41],"wrapped,":[45],"unwrapped":[46],"minimum-phase":[48],"spectra":[50],"as":[51,53],"well":[52],"source":[58],"filter":[60],"components":[61,79],"modelling.":[64],"Furthermore,":[65],"explore":[67],"effectiveness":[69],"simultaneous":[71],"deployment":[72],"vocal":[75],"tract":[76],"excitation":[78],"spectrum":[84],"multi-head":[86],"CNNs":[87],"multiple":[90],"information":[91,104],"fusion":[92],"schemes.":[93],"This":[94],"paves":[95],"way":[97],"developing":[99],"an":[100],"effective":[101],"phase-based":[102],"multi-stream":[103],"processing":[105],"systems":[106],"recognition.":[109],"The":[110],"performance,":[111],"even":[112],"wrapped":[114],"with":[116],"a":[117],"noise-like":[118],"shape,":[119],"is":[120],"comparable":[121],"to":[122,132],"or":[123],"better":[124],"than":[125],"magnitude-based":[127],"classic":[128],"features,":[129],"up":[131],"4.8%":[133],"WER":[134],"has":[135],"been":[136],"achieved":[137],"WSJ":[140],"(Eval-92)":[141],"task.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}