{"id":"https://openalex.org/W3114907617","doi":"https://doi.org/10.1186/s13636-021-00198-4","title":"A CNN-based approach to identification of degradations in speech signals","display_name":"A CNN-based approach to identification of degradations in speech signals","publication_year":2021,"publication_date":"2021-02-05","ids":{"openalex":"https://openalex.org/W3114907617","doi":"https://doi.org/10.1186/s13636-021-00198-4","mag":"3114907617"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00198-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00198-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00198-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00198-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079859605","display_name":"Yuki Saishu","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Yuki Saishu","raw_affiliation_strings":["Audio Analysis Lab, CREATE, Aalborg University, Rendsburggade 14, Aalborg, 9000, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Rendsburggade 14, Aalborg, 9000, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019002740","display_name":"Amir Hossein Poorjam","orcid":"https://orcid.org/0000-0002-6882-4618"},"institutions":[{"id":"https://openalex.org/I4210112936","display_name":"Verisk Analytics (United States)","ror":"https://ror.org/01xdzbt45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112936"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK","US"],"is_corresponding":true,"raw_author_name":"Amir Hossein Poorjam","raw_affiliation_strings":["Audio Analysis Lab, CREATE, Aalborg University, Rendsburggade 14, Aalborg, 9000, Denmark","Verisk Analytics, 388 Market Street, San Francisco, 94111, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6882-4618","affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Rendsburggade 14, Aalborg, 9000, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Verisk Analytics, 388 Market Street, San Francisco, 94111, CA, USA","institution_ids":["https://openalex.org/I4210112936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Audio Analysis Lab, CREATE, Aalborg University, Rendsburggade 14, Aalborg, 9000, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Rendsburggade 14, Aalborg, 9000, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019002740"],"corresponding_institution_ids":["https://openalex.org/I4210112936","https://openalex.org/I891191580"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.0919,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80756659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"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":0.9994000196456909,"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":0.9012420177459717},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6676172018051147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6085842847824097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3897341191768646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37846875190734863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3601507544517517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9012420177459717},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6676172018051147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6085842847824097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3897341191768646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37846875190734863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3601507544517517},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-021-00198-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00198-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00198-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/782eac05-b345-4cbc-bdfd-6043f49f8f0c","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/782eac05-b345-4cbc-bdfd-6043f49f8f0c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"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":"Saishu, Y, Poorjam, A H & Christensen, M G 2021, 'A CNN-Based Approach to Identification of Degradations in Speech Signals', Eurasip Journal on Audio, Speech, and Music Processing, vol. 2021, no. 1, 9, pp. 1-10. https://doi.org/10.1186/s13636-021-00198-4","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:ae4eedb1b11f4b31a901e1994f929588","is_oa":true,"landing_page_url":"https://doaj.org/article/ae4eedb1b11f4b31a901e1994f929588","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-10 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00198-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00198-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00198-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6797287447","display_name":null,"funder_award_id":"DFF 4184-00056","funder_id":"https://openalex.org/F4320327387","funder_display_name":"Danmarks Frie Forskningsfond"}],"funders":[{"id":"https://openalex.org/F4320327387","display_name":"Danmarks Frie Forskningsfond","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114907617.pdf","grobid_xml":"https://content.openalex.org/works/W3114907617.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W914169429","https://openalex.org/W1808196926","https://openalex.org/W1971243715","https://openalex.org/W1973354160","https://openalex.org/W1973746598","https://openalex.org/W1983108229","https://openalex.org/W1984501117","https://openalex.org/W1992595735","https://openalex.org/W2006129368","https://openalex.org/W2006715209","https://openalex.org/W2013020033","https://openalex.org/W2029362727","https://openalex.org/W2035826116","https://openalex.org/W2040992166","https://openalex.org/W2045784978","https://openalex.org/W2069441775","https://openalex.org/W2086286498","https://openalex.org/W2104953067","https://openalex.org/W2151626637","https://openalex.org/W2296350496","https://openalex.org/W2394812591","https://openalex.org/W2395913652","https://openalex.org/W2562673262","https://openalex.org/W2605398097","https://openalex.org/W2609317876","https://openalex.org/W2748130992","https://openalex.org/W2757519008","https://openalex.org/W2762101354","https://openalex.org/W2802822582","https://openalex.org/W2962835968","https://openalex.org/W2963702144","https://openalex.org/W2964285380","https://openalex.org/W2978880690","https://openalex.org/W2994926924","https://openalex.org/W2996061341","https://openalex.org/W2998843375","https://openalex.org/W3199902496","https://openalex.org/W4237729708","https://openalex.org/W4251733995","https://openalex.org/W4297675714","https://openalex.org/W6600260580","https://openalex.org/W6600737549","https://openalex.org/W6601547425","https://openalex.org/W6633546298"],"related_works":["https://openalex.org/W2898732673","https://openalex.org/W2410053581","https://openalex.org/W2383658677","https://openalex.org/W3123203398","https://openalex.org/W1972473893","https://openalex.org/W2466435674","https://openalex.org/W2765200542","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"presence":[2,56,144],"of":[3,20,26,60,83,102,117,137,148,170,180,189],"degradations":[4,61,84,149],"in":[5,37,62,87,141,150,182],"speech":[6,63,125,151,183],"signals,":[7],"which":[8,153,193],"causes":[9],"acoustic":[10,35],"mismatch":[11,36],"between":[12],"training":[13],"and":[14,57,95,130,145],"operating":[15],"conditions,":[16],"deteriorates":[17],"the":[18,34,55,58,80,114,135,138,143,146,155,159,172,187,190,198],"performance":[19],"many":[21],"speech-based":[22,38,88],"systems.":[23],"A":[24],"variety":[25],"enhancement":[27,44],"techniques":[28],"have":[29],"been":[30],"developed":[31],"to":[32,50,77,113,197],"compensate":[33],"applications.":[39],"To":[40],"apply":[41],"these":[42],"signal":[43],"techniques,":[45],"however,":[46],"it":[47],"is":[48,111],"necessary":[49],"know":[51],"prior":[52],"information":[53],"about":[54],"type":[59,147],"signals.":[64,119],"In":[65,97],"this":[66,98],"paper,":[67],"we":[68,165],"propose":[69],"a":[70,100,107,167],"new":[71],"convolutional":[72],"neural":[73],"network":[74,173],"(CNN)-based":[75],"approach":[76],"automatically":[78],"identify":[79],"major":[81],"types":[82,179],"commonly":[85],"encountered":[86],"applications,":[89],"namely":[90,127],"additive":[91],"noise,":[92],"nonlinear":[93],"distortion,":[94],"reverberation.":[96],"approach,":[99],"set":[101],"parallel":[103],"CNNs,":[104],"each":[105],"detecting":[106,142],"certain":[108],"degradation":[109,181],"type,":[110],"applied":[112],"log-mel":[115,191],"spectrogram":[116,192],"audio":[118],"Experimental":[120],"results":[121],"using":[122],"two":[123],"different":[124,178],"types,":[126],"pathological":[128],"voice":[129],"normal":[131],"running":[132],"speech,":[133],"show":[134],"effectiveness":[136],"proposed":[139],"method":[140],"signals":[152,184],"outperforms":[154],"state-of-the-art":[156],"method.":[157],"Using":[158],"score":[160],"weighted":[161],"class":[162],"activation":[163],"mapping,":[164],"provide":[166],"visual":[168],"analysis":[169],"how":[171],"makes":[174],"decision":[175],"for":[176],"identifying":[177],"by":[185],"highlighting":[186],"regions":[188],"are":[194],"more":[195],"influential":[196],"target":[199],"degradation.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}