{"id":"https://openalex.org/W2888957357","doi":"https://doi.org/10.21437/interspeech.2018-2458","title":"Effectiveness of Single-Channel BLSTM Enhancement for Language Identification","display_name":"Effectiveness of Single-Channel BLSTM Enhancement for Language Identification","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888957357","doi":"https://doi.org/10.21437/interspeech.2018-2458","mag":"2888957357"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2458","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/36419f0f-65ad-4db3-8d7b-a4757aa84033","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013389702","display_name":"Peter Sibbern Frederiksen","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":"Peter Sibbern Frederiksen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110494768","display_name":"Zheng-Hua Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"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":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1823","last_page":"1827"},"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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.8363285064697266},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7757047414779663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.774378776550293},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7418181896209717},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5545371174812317},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5210103988647461},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5163025259971619},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5146604180335999},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5062841176986694},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4712767004966736},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.447290301322937},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4399726986885071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4253336489200592},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.14797565340995789},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12088096141815186},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08382925391197205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363285064697266},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7757047414779663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.774378776550293},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7418181896209717},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5545371174812317},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5210103988647461},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5163025259971619},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5146604180335999},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5062841176986694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4712767004966736},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.447290301322937},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4399726986885071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4253336489200592},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.14797565340995789},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12088096141815186},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08382925391197205},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-2458","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/36419f0f-65ad-4db3-8d7b-a4757aa84033","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/36419f0f-65ad-4db3-8d7b-a4757aa84033","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":"Sibbern Frederiksen, P, Villalba, J, Watanabe, S, Tan, Z-H & Dehak, N 2018, Effectiveness of Single-Channel BLSTM Enhancement for Language Identification. in Interspeech 2018. vol. 2018-September, ISCA, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 1823-1827, Interspeech 2018, Hyderabad, India, 02/09/2018. https://doi.org/10.21437/Interspeech.2018-2458","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/36419f0f-65ad-4db3-8d7b-a4757aa84033","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85055006254&partnerID=8YFLogxK","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sibbern Frederiksen , P , Villalba , J , Watanabe , S , Tan , Z-H & Dehak , N 2018 , Effectiveness of Single-Channel BLSTM Enhancement for Language Identification . in Interspeech 2018 . vol. 2018-September , ISCA , Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH , pp. 1823-1827 , Interspeech 2018 , Hyderabad , India , 02/09/2018 . https://doi.org/10.21437/Interspeech.2018-2458","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/36419f0f-65ad-4db3-8d7b-a4757aa84033","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/36419f0f-65ad-4db3-8d7b-a4757aa84033","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":"Sibbern Frederiksen, P, Villalba, J, Watanabe, S, Tan, Z-H & Dehak, N 2018, Effectiveness of Single-Channel BLSTM Enhancement for Language Identification. in Interspeech 2018. vol. 2018-September, ISCA, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 1823-1827, Interspeech 2018, Hyderabad, India, 02/09/2018. https://doi.org/10.21437/Interspeech.2018-2458","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W5151113","https://openalex.org/W1482149378","https://openalex.org/W1524333225","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W2027701650","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2150769028","https://openalex.org/W2160003195","https://openalex.org/W2219249508","https://openalex.org/W2405774341","https://openalex.org/W2516001803","https://openalex.org/W2550397165","https://openalex.org/W2559260703","https://openalex.org/W2746457594","https://openalex.org/W2805603126"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W1998541766","https://openalex.org/W2262900283","https://openalex.org/W1985349217","https://openalex.org/W2098508228","https://openalex.org/W2624072012","https://openalex.org/W1508853749","https://openalex.org/W69308499"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"to":[3,13,29,44,53,76,82,128,155],"apply":[4],"deep":[5],"neural":[6,101],"network":[7],"(DNN)-based":[8],"single-channel":[9],"speech":[10,43,46,79,148],"enhancement":[11,80],"(SE)":[12],"language":[14,18,91,156],"identification.":[15,92],"The":[16,119,150],"2017":[17],"recognition":[19],"evaluation":[20],"(LRE17)":[21],"introduced":[22],"noisy":[23,45,86,106,120,147,159,192],"audios":[24],"from":[25,33,41,47],"videos,":[26],"in":[27,173],"addition":[28],"the":[30,48,63,85,130,140,145,170,174,179,186],"telephone":[31,42,175],"conversation":[32],"past":[34],"challenges.":[35],"Because":[36],"of":[37,62,68,72,158],"that,":[38],"adapting":[39],"models":[40],"video":[49],"domain":[50,65,142,166],"was":[51],"required":[52],"obtain":[54,129],"optimum":[55],"performance.":[56],"However,":[57],"such":[58],"adaptation":[59],"requires":[60],"knowledge":[61],"audio":[64,87,176],"and":[66,134,164],"availability":[67],"in-domain":[69],"data.":[70],"Instead":[71],"adaptation,":[73,167],"we":[74],"propose":[75],"use":[77],"a":[78,95,109],"step":[81],"clean":[83,114],"up":[84],"as":[88],"preprocessing":[89],"for":[90,161,191],"We":[93],"used":[94],"bi-directional":[96],"long":[97],"short-term":[98],"memory":[99],"(BLSTM)":[100],"network,":[102],"which":[103],"given":[104],"log-Mel":[105],"features":[107],"predicts":[108],"spectral":[110],"mask":[111,127],"indicating":[112],"how":[113],"each":[115],"time-frequency":[116],"bin":[117],"is.":[118],"spectrogram":[121],"is":[122,136,189],"multiplied":[123],"by":[124,143],"this":[125],"predicted":[126],"enhanced":[131],"magnitude":[132],"spectrogram,":[133],"it":[135],"transformed":[137],"back":[138],"into":[139],"time":[141],"using":[144],"unaltered":[146],"phase.":[149],"experiments":[151],"show":[152],"significant":[153],"improvement":[154,188],"identification":[157,171],"speech,":[160],"systems":[162],"with":[163],"without":[165],"while":[168],"preserving":[169],"performance":[172],"domain.":[177],"In":[178],"best":[180],"adapted":[181],"state-of-the-art":[182],"bottleneck":[183],"i-vector":[184],"system":[185],"relative":[187],"11.3%":[190],"speech.":[193]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}