{"id":"https://openalex.org/W4319998061","doi":"https://doi.org/10.1109/taslp.2023.3237167","title":"Multi-Stream Acoustic Modelling Using Raw Real and Imaginary Parts of the Fourier Transform","display_name":"Multi-Stream Acoustic Modelling Using Raw Real and Imaginary Parts of the Fourier Transform","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319998061","doi":"https://doi.org/10.1109/taslp.2023.3237167"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3237167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3237167","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kclpure.kcl.ac.uk/portal/en/publications/d66b1693-03aa-463f-b38b-9a1f09125563","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/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"]},{"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"]},{"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":["King's College London (KCL), London, U.K","Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8761-021X","affiliations":[{"raw_affiliation_string":"King's College London (KCL), London, U.K","institution_ids":["https://openalex.org/I4210119896","https://openalex.org/I183935753"]},{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053209750","display_name":"Zhengjun Yue","orcid":"https://orcid.org/0000-0002-1101-549X"},"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"]},{"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":"Zhengjun Yue","raw_affiliation_strings":["King's College London (KCL), London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1101-549X","affiliations":[{"raw_affiliation_string":"King's College London (KCL), London, U.K","institution_ids":["https://openalex.org/I4210119896","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":[{"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":["Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-9597-9615","affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8790-3389","affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","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"]},{"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 (KCL), London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5128-5099","affiliations":[{"raw_affiliation_string":"King's College London (KCL), London, U.K","institution_ids":["https://openalex.org/I4210119896","https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1211,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8940268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"876","last_page":"890"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.6067599058151245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.560765266418457},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.46568337082862854},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44355452060699463},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.411484032869339},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.394656777381897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35476064682006836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21356865763664246},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.10168585181236267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067599058151245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.560765266418457},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.46568337082862854},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44355452060699463},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.411484032869339},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.394656777381897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35476064682006836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21356865763664246},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.10168585181236267},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/taslp.2023.3237167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3237167","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/d66b1693-03aa-463f-b38b-9a1f09125563","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/d66b1693-03aa-463f-b38b-9a1f09125563","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Loweimi, E, Yue, Z, Bell, P, Renals, S & Cvetkovic, Z 2022, 'Multi-stream Acoustic Modelling using Raw Real and Imaginary Parts of the Fourier Transform', IEEE/ACM Transactions on Audio, Speech, and Language Processing .","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/d66b1693-03aa-463f-b38b-9a1f09125563","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/multistream-acoustic-modelling-using-raw-real-and-imaginary-parts-of-the-fourier-transform(d66b1693-03aa-463f-b38b-9a1f09125563).html","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":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/136b20e3-3498-463f-a549-379a95288295","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/136b20e3-3498-463f-a549-379a95288295","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/136b20e3-3498-463f-a549-379a95288295","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/326802049/Multi_Stream_Acoustic_LOWEIMI_DOA06012023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Loweimi, E, Yue, Z, Bell, P, Renals, S & Cvetkovic, Z 2023, 'Multi-stream Acoustic Modelling using Raw Real and Imaginary Parts of the Fourier Transform', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 31, pp. 876-890. https://doi.org/10.1109/TASLP.2023.3237167","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository@napier.ac.uk:3585794","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585794","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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/d66b1693-03aa-463f-b38b-9a1f09125563","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/d66b1693-03aa-463f-b38b-9a1f09125563","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Loweimi, E, Yue, Z, Bell, P, Renals, S & Cvetkovic, Z 2022, 'Multi-stream Acoustic Modelling using Raw Real and Imaginary Parts of the Fourier Transform', IEEE/ACM Transactions on Audio, Speech, and Language Processing .","raw_type":"info:eu-repo/semantics/publishedVersion"},"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":79,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1566256432","https://openalex.org/W1635512741","https://openalex.org/W2009562705","https://openalex.org/W2013046930","https://openalex.org/W2018363392","https://openalex.org/W2025920047","https://openalex.org/W2060108923","https://openalex.org/W2067295501","https://openalex.org/W2090861223","https://openalex.org/W2095705004","https://openalex.org/W2095992616","https://openalex.org/W2097775139","https://openalex.org/W2099111195","https://openalex.org/W2101304342","https://openalex.org/W2101596234","https://openalex.org/W2109770219","https://openalex.org/W2114992418","https://openalex.org/W2116217121","https://openalex.org/W2120847449","https://openalex.org/W2130361043","https://openalex.org/W2131548063","https://openalex.org/W2140828385","https://openalex.org/W2141134251","https://openalex.org/W2144121180","https://openalex.org/W2148154194","https://openalex.org/W2168249605","https://openalex.org/W2288217446","https://openalex.org/W2398195950","https://openalex.org/W2398826216","https://openalex.org/W2404126548","https://openalex.org/W2408093180","https://openalex.org/W2488580825","https://openalex.org/W2504507112","https://openalex.org/W2506203739","https://openalex.org/W2508048623","https://openalex.org/W2511710182","https://openalex.org/W2512499206","https://openalex.org/W2566079294","https://openalex.org/W2579029485","https://openalex.org/W2589857635","https://openalex.org/W2594170997","https://openalex.org/W2798405286","https://openalex.org/W2805215415","https://openalex.org/W2938901746","https://openalex.org/W2963747784","https://openalex.org/W2964052309","https://openalex.org/W2964227577","https://openalex.org/W2973053574","https://openalex.org/W2995025901","https://openalex.org/W3016042429","https://openalex.org/W3094855746","https://openalex.org/W3094861110","https://openalex.org/W3095947083","https://openalex.org/W3095950035","https://openalex.org/W3096891716","https://openalex.org/W3097777922","https://openalex.org/W3098473349","https://openalex.org/W3163211337","https://openalex.org/W3163845842","https://openalex.org/W3191151211","https://openalex.org/W3195185666","https://openalex.org/W3197553328","https://openalex.org/W3197737164","https://openalex.org/W4206319965","https://openalex.org/W4224918597","https://openalex.org/W4232318280","https://openalex.org/W4236328885","https://openalex.org/W4253928870","https://openalex.org/W4255949318","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6633847657","https://openalex.org/W6640464412","https://openalex.org/W6674330103","https://openalex.org/W6732256780","https://openalex.org/W6738884980","https://openalex.org/W6752308553","https://openalex.org/W6785296793"],"related_works":["https://openalex.org/W4225639054","https://openalex.org/W2368779261","https://openalex.org/W4200633555","https://openalex.org/W2000534859","https://openalex.org/W2127461790","https://openalex.org/W2134867751","https://openalex.org/W2067120597","https://openalex.org/W4213137765","https://openalex.org/W2021850870","https://openalex.org/W2078030874"],"abstract_inverted_index":{"In":[0,66,223],"this":[1],"paper,":[2],"we":[3,178,230],"investigate":[4],"multi-stream":[5,145],"acoustic":[6],"modelling":[7],"using":[8],"the":[9,16,23,36,54,67,70,129,134,138,151,154,206,214],"raw":[10,24],"real":[11,37,71],"and":[12,38,46,52,64,72,87,102,124,131,144,171,195,200,212,227,235],"imaginary":[13,39,73],"parts":[14,40,74],"of":[15,19,56,61,80,94,108,118,133,142,153,205],"Fourier":[17],"transform":[18],"speech":[20,62,229],"signals.":[21],"Using":[22],"magnitude":[25],"spectrum,":[26],"or":[27],"features":[28],"derived":[29],"from":[30],"it,":[31],"as":[32,77,126,128],"a":[33],"proxy":[34],"for":[35,198,202,225],"leads":[41],"to":[42,185,193,209,217,233],"irreversible":[43],"information":[44,48,58,109],"loss":[45],"suboptimal":[47],"fusion.":[49],"We":[50,149],"discuss":[51],"quantify":[53],"importance":[55],"such":[57],"in":[59,111,116,137,157,182,190,213],"terms":[60,117],"quality":[63],"intelligibility.":[65],"proposed":[68,155],"framework,":[69],"are":[75,147],"treated":[76],"two":[78],"streams":[79],"information,":[81],"pre-processed":[82],"via":[83,100],"separate":[84],"convolutional":[85,140],"networks,":[86],"then":[88],"combined":[89],"at":[90],"an":[91],"optimal":[92,106],"level":[93,107],"abstraction,":[95],"followed":[96],"by":[97],"further":[98],"post-processing":[99],"recurrent":[101],"fully-connected":[103],"layers.":[104],"The":[105],"fusion":[110],"various":[112,158],"architectures,":[113],"training":[114],"dynamics":[115],"cross-entropy":[119],"loss,":[120],"frame":[121],"classification":[122],"accuracy":[123],"WER":[125,187],"well":[127],"shape":[130],"properties":[132],"filters":[135],"learned":[136],"first":[139],"layer":[141],"single-":[143],"models":[146],"analysed.":[148],"investigated":[150],"effectiveness":[152],"systems":[156],"tasks:":[159],"TIMIT/NTIMIT":[160],"(phone":[161],"recognition),":[162],"Aurora-4":[163],"(noise":[164],"robustness),":[165],"WSJ":[166,191],"(read":[167],"speech),":[168],"AMI":[169],"(meeting)":[170],"TORGO":[172],"(dysarthric":[173],"speech).":[174],"Across":[175],"all":[176],"tasks":[177],"achieved":[179,231],"competitive":[180],"performance:":[181],"Aurora-4,":[183],"down":[184,192,208,216,232],"4.6%":[186,194],"on":[188],"average,":[189],"6.2%":[196],"WERs":[197,211,219],"Eval-92":[199],"Eval-93,":[201],"Dev/Eval":[203],"sets":[204],"AMI-IHM":[207],"23.3%/23.8%":[210],"AMI-SDM":[215],"43.7%/47.6%":[218],"have":[220],"been":[221],"achieved.":[222],"TORGO,":[224],"dysarthric":[226],"typical":[228],"31.7%":[234],"10.2%":[236],"WERs,":[237],"respectively.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}