{"id":"https://openalex.org/W2640905660","doi":"https://doi.org/10.1109/icassp.2017.7953096","title":"Normal-to-shouted speech spectral mapping for speaker recognition under vocal effort mismatch","display_name":"Normal-to-shouted speech spectral mapping for speaker recognition under vocal effort mismatch","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2640905660","doi":"https://doi.org/10.1109/icassp.2017.7953096","mag":"2640905660"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110044024","display_name":"Ana Ram\u00edrez L\u00f3pez","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ana Ramirez Lopez","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023224767","display_name":"Rahim Saeidi","orcid":"https://orcid.org/0000-0002-9084-0091"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Rahim Saeidi","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081575688","display_name":"Lauri Juvela","orcid":"https://orcid.org/0000-0002-2201-103X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lauri Juvela","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.969,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80255066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"48","issue":null,"first_page":"4940","last_page":"4944"},"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":0.9991000294685364,"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":0.9943000078201294,"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/speech-recognition","display_name":"Speech recognition","score":0.846840500831604},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7613376379013062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.751993715763092},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5896346569061279},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.545231819152832},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5221027135848999},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46249106526374817},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41283366084098816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38065779209136963}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.846840500831604},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7613376379013062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751993715763092},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5896346569061279},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.545231819152832},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5221027135848999},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46249106526374817},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41283366084098816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38065779209136963},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W808445616","https://openalex.org/W1535737202","https://openalex.org/W1555937754","https://openalex.org/W1587896874","https://openalex.org/W1625928172","https://openalex.org/W1916834241","https://openalex.org/W1936725236","https://openalex.org/W1968331495","https://openalex.org/W2008557021","https://openalex.org/W2022895291","https://openalex.org/W2031887434","https://openalex.org/W2038875793","https://openalex.org/W2049409082","https://openalex.org/W2058542017","https://openalex.org/W2063656732","https://openalex.org/W2075208738","https://openalex.org/W2086381991","https://openalex.org/W2117045222","https://openalex.org/W2121812409","https://openalex.org/W2121892718","https://openalex.org/W2123003832","https://openalex.org/W2125514156","https://openalex.org/W2146368056","https://openalex.org/W2150769028","https://openalex.org/W2156142001","https://openalex.org/W2296704011","https://openalex.org/W2333836441","https://openalex.org/W2400893182","https://openalex.org/W2619183452","https://openalex.org/W6623044552","https://openalex.org/W6633163937","https://openalex.org/W6636443714","https://openalex.org/W6640010188","https://openalex.org/W6677847058","https://openalex.org/W6697285287"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Speaker":[0],"recognition":[1,74,110],"performance":[2,71,104],"degrades":[3],"substantially":[4],"in":[5,29,61,72,134,137],"case":[6],"of":[7,55,105],"vocal":[8,77],"effort":[9,78],"mismatch":[10,23,79],"(e.g.":[11],"shouted":[12,62],"vs.":[13],"normal":[14,56],"speech)":[15],"between":[16,80],"test":[17,83],"and":[18,82,113],"enrollment":[19,81,122],"utterances.":[20,84],"Such":[21],"a":[22,36,46,106],"is":[24,66,87],"often":[25],"encountered,":[26],"for":[27],"example,":[28],"forensic":[30],"speaker":[31,73,109],"recognition.":[32],"This":[33],"paper":[34],"introduces":[35],"novel":[37],"spectral":[38,117],"mapping":[39,48,118],"method":[40],"which,":[41],"when":[42],"employed":[43],"jointly":[44],"with":[45,112,129],"statistical":[47],"technique,":[49],"converts":[50],"the":[51,90,103,116,121,130],"Mel-frequency":[52],"band":[53],"energies":[54],"speech":[57,91],"towards":[58],"their":[59],"counterparts":[60],"speech.":[63],"The":[64,85,96,124],"aim":[65],"to":[67,120],"obtain":[68],"more":[69],"robust":[70],"by":[75,101],"tackling":[76],"processing":[86,119],"performed":[88],"on":[89],"signal":[92],"before":[93],"feature":[94],"extraction.":[95],"proposed":[97,131],"approach":[98,132],"was":[99],"evaluated":[100],"testing":[102],"state-of-the-art":[107],"i-vector-based":[108],"system":[111],"without":[114],"applying":[115],"data.":[123],"results":[125,133],"show":[126],"that":[127],"pre-processing":[128],"considerable":[135],"improvement":[136],"correct":[138],"identification":[139],"rates.":[140]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}