{"id":"https://openalex.org/W2802812753","doi":"https://doi.org/10.1109/icassp.2018.8462459","title":"A Supervised Approach to Global Signal-to-Noise Ratio Estimation for Whispered and Pathological Voices","display_name":"A Supervised Approach to Global Signal-to-Noise Ratio Estimation for Whispered and Pathological Voices","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802812753","doi":"https://doi.org/10.1109/icassp.2018.8462459","mag":"2802812753"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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://vbn.aau.dk/da/publications/e0e5d796-b29b-4950-b7f9-48b8042f6660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019002740","display_name":"Amir Hossein Poorjam","orcid":"https://orcid.org/0000-0002-6882-4618"},"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":"Amir Hossein Poorjam","raw_affiliation_strings":["Audio Analysis Lab, Aalborg University, Aalborg, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, Aalborg University, Aalborg, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018028924","display_name":"Max A. Little","orcid":"https://orcid.org/0000-0002-1507-3822"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Max A. Little","raw_affiliation_strings":["Engineering and Applied Science, Aston University, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering and Applied Science, Aston University, Birmingham, UK","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041263382","display_name":"Jesper Rindom Jensen","orcid":"https://orcid.org/0000-0001-6023-8270"},"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":"Jesper Rindom Jensen","raw_affiliation_strings":["Audio Analysis Lab, Aalborg University, Aalborg, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, Aalborg University, Aalborg, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"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 Graesboll Christensen","raw_affiliation_strings":["Audio Analysis Lab, Aalborg University, Aalborg, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, Aalborg University, Aalborg, DK","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1639,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79084925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":null,"first_page":"296","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7402506470680237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.72454434633255},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6781772971153259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6517051458358765},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5908423662185669},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5703743696212769},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4946705996990204},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4909968674182892},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48951852321624756},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.45494744181632996},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4261133372783661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3945241868495941},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.273650586605072},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23812758922576904},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21726715564727783},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.14205673336982727},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10956501960754395}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7402506470680237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.72454434633255},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6781772971153259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517051458358765},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5908423662185669},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5703743696212769},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4946705996990204},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4909968674182892},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48951852321624756},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.45494744181632996},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4261133372783661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3945241868495941},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.273650586605072},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23812758922576904},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21726715564727783},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.14205673336982727},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10956501960754395},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2018.8462459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/e0e5d796-b29b-4950-b7f9-48b8042f6660","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/e0e5d796-b29b-4950-b7f9-48b8042f6660","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":"Poorjam, A H, Little, M A, Jensen, J R & Christensen, M G 2018, A Supervised Approach to Global Signal-to-Noise Ratio Estimation for Whispered and Pathological Voices. in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 8462459, IEEE (Institute of Electrical and Electronics Engineers), I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 296-300, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, 15/04/2018. https://doi.org/10.1109/ICASSP.2018.8462459","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:publications.aston.ac.uk:37278","is_oa":true,"landing_page_url":"https://publications.aston.ac.uk/view/author/55854151225fae1984fe9ab94da9b586.html>,","pdf_url":"https://publications.aston.ac.uk/id/eprint/37278/1/ICASSP_amir_4108.pdf","source":{"id":"https://openalex.org/S4306400483","display_name":"Aston Publications Explorer (Aston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169199633","host_organization_name":"Aston University","host_organization_lineage":["https://openalex.org/I169199633"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/e0e5d796-b29b-4950-b7f9-48b8042f6660","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/e0e5d796-b29b-4950-b7f9-48b8042f6660","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":"Poorjam, A H, Little, M A, Jensen, J R & Christensen, M G 2018, A Supervised Approach to Global Signal-to-Noise Ratio Estimation for Whispered and Pathological Voices. in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 8462459, IEEE (Institute of Electrical and Electronics Engineers), I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 296-300, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, 15/04/2018. https://doi.org/10.1109/ICASSP.2018.8462459","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W187652810","https://openalex.org/W1493163583","https://openalex.org/W1494198834","https://openalex.org/W1574170747","https://openalex.org/W1964357740","https://openalex.org/W1986225048","https://openalex.org/W2013312573","https://openalex.org/W2079918934","https://openalex.org/W2094709280","https://openalex.org/W2104953067","https://openalex.org/W2106214098","https://openalex.org/W2120933697","https://openalex.org/W2138456300","https://openalex.org/W2144561273","https://openalex.org/W2156909104","https://openalex.org/W2166943505","https://openalex.org/W2180339972","https://openalex.org/W2529545010","https://openalex.org/W2597292025","https://openalex.org/W2748130992","https://openalex.org/W4230674625","https://openalex.org/W6607758474","https://openalex.org/W6634468015","https://openalex.org/W6684352069","https://openalex.org/W6734843831","https://openalex.org/W6743124364"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W334008168","https://openalex.org/W2535773091"],"abstract_inverted_index":{"The":[0],"presence":[1],"of":[2,11,17,23,79,87,103,112,123,151],"background":[3],"noise":[4,24,34,83,119,129,174],"in":[5,26,31],"signals":[6],"adversely":[7],"affects":[8],"the":[9,77,85,104,107,110,121,128,152,159],"performance":[10,167],"many":[12],"speech-based":[13],"algorithms.":[14],"Accurate":[15],"estimation":[16,39,52,140,164],"signal-to-noise-ratio":[18],"(SNR),":[19],"as":[20,58],"a":[21,27,134,145],"measure":[22],"level":[25],"signal,":[28],"can":[29],"help":[30],"compensating":[32],"for":[33,44,53,138,168],"effects.":[35],"Most":[36],"existing":[37],"SNR":[38,139],"methods":[40],"have":[41],"been":[42],"developed":[43],"normal":[45],"speech":[46,55,105,170],"and":[47,81,96,109,120,165],"might":[48],"not":[49],"provide":[50],"accurate":[51,163],"special":[54],"types":[56,171],"such":[57],"whispered":[59,95],"or":[60],"disordered":[61],"voices,":[62],"particularly,":[63],"when":[64],"they":[65],"are":[66,114],"corrupted":[67],"by":[68,117],"non-stationary":[69,82],"noises.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74,132],"first":[75],"investigate":[76],"impact":[78],"stationary":[80],"on":[84,144,149],"behavior":[86],"mel-frequency":[88],"cepstral":[89],"coefficients":[90],"(MFCCs)":[91],"extracted":[92],"from":[93],"normal,":[94],"pathological":[97],"voices.":[98],"We":[99],"demonstrate":[100],"that,":[101],"regardless":[102],"type,":[106],"mean":[108],"covariance":[111],"MFCCs":[113,150],"predictably":[115],"modified":[116],"additive":[118],"amount":[122],"change":[124],"is":[125,142],"related":[126],"to":[127],"level.":[130],"Then,":[131],"propose":[133],"new":[135],"supervised":[136],"method":[137],"which":[141],"based":[143],"regression":[146],"model":[147],"trained":[148],"noisy":[153],"signals.":[154],"Experimental":[155],"results":[156],"show":[157],"that":[158],"proposed":[160],"approach":[161],"provides":[162],"consistent":[166],"various":[169],"under":[172],"different":[173],"conditions.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}