{"id":"https://openalex.org/W4206631948","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660563","title":"Investigation of a Single-Channel Frequency-Domain Speech Enhancement Network to Improve End-to-End Bengali Automatic Speech Recognition Under Unseen Noisy Conditions","display_name":"Investigation of a Single-Channel Frequency-Domain Speech Enhancement Network to Improve End-to-End Bengali Automatic Speech Recognition Under Unseen Noisy Conditions","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4206631948","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660563"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"article","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/A5020780039","display_name":"Md Mahbub E Noor","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Md Mahbub E Noor","raw_affiliation_strings":["National Tsing Hua University, Taiwan","Taiwan International Graduate Program in Social Network and Human-Centered Computing, Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Taiwan International Graduate Program in Social Network and Human-Centered Computing, Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067198078","display_name":"Yen-Ju Lu","orcid":"https://orcid.org/0000-0001-8400-4188"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Ju Lu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046122","display_name":"Syu\u2010Siang Wang","orcid":"https://orcid.org/0000-0002-2652-5521"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Syu-Siang Wang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072901003","display_name":"Supratip Ghose","orcid":null},"institutions":[{"id":"https://openalex.org/I142758973","display_name":"University of Information Technology and Sciences","ror":"https://ror.org/04j1jjs80","country_code":"BD","type":"education","lineage":["https://openalex.org/I142758973"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Supratip Ghose","raw_affiliation_strings":["University of Information Technology & Sciences, Bangladesh"],"affiliations":[{"raw_affiliation_string":"University of Information Technology & Sciences, Bangladesh","institution_ids":["https://openalex.org/I142758973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009566669","display_name":"Chia\u2010Yu Chang","orcid":"https://orcid.org/0000-0002-7020-8451"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Yu Chang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030281426","display_name":"Ryandhimas E. Zezario","orcid":"https://orcid.org/0000-0001-7319-8263"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ryandhimas E. Zezario","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037771864","display_name":"Shafique Ahmed","orcid":"https://orcid.org/0000-0001-6206-8674"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shafique Ahmed","raw_affiliation_strings":["National Tsing Hua University, Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035844880","display_name":"Wei\u2010Ho Chung","orcid":"https://orcid.org/0000-0002-3041-7398"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Ho Chung","raw_affiliation_strings":["National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Taiwan International Graduate Program in Social Network and Human-Centered Computing, Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Taiwan International Graduate Program in Social Network and Human-Centered Computing, Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5020780039"],"corresponding_institution_ids":["https://openalex.org/I25846049","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.3047,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5709263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"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":0.9998000264167786,"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":0.9904999732971191,"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":0.8082870841026306},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.806365430355072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.697751522064209},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6927893161773682},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6121079325675964},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5548485517501831},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4485718011856079},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4352940320968628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42652779817581177},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2157372534275055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0955471396446228},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07242953777313232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082870841026306},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.806365430355072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.697751522064209},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6927893161773682},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6121079325675964},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5548485517501831},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4485718011856079},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4352940320968628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42652779817581177},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2157372534275055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0955471396446228},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07242953777313232},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda202152914.2021.9660563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1552314771","https://openalex.org/W1598508708","https://openalex.org/W2000916836","https://openalex.org/W2113131123","https://openalex.org/W2141998673","https://openalex.org/W2143612262","https://openalex.org/W2159202424","https://openalex.org/W2327501763","https://openalex.org/W2405774341","https://openalex.org/W2627092829","https://openalex.org/W2755891984","https://openalex.org/W2766219058","https://openalex.org/W2895676041","https://openalex.org/W2935934262","https://openalex.org/W2936774411","https://openalex.org/W2937998856","https://openalex.org/W2962780374","https://openalex.org/W2972412503","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015219411","https://openalex.org/W3015312544","https://openalex.org/W3035903835","https://openalex.org/W3094932283","https://openalex.org/W3098784505","https://openalex.org/W3103003256","https://openalex.org/W3132954452","https://openalex.org/W4210849719","https://openalex.org/W4253928870","https://openalex.org/W4289242435","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6635900476","https://openalex.org/W6739901393","https://openalex.org/W6756251360","https://openalex.org/W6773419339","https://openalex.org/W6780226713","https://openalex.org/W6790758941"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W3043214604","https://openalex.org/W1505346162","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"Due":[0],"to":[1,49,83],"the":[2,8,85,100,133],"presence":[3],"of":[4,7,135],"distortion,":[5],"most":[6],"single-channel":[9],"frequency-domain":[10],"speech":[11,21,31,43],"enhancement":[12],"(SE)":[13],"approaches":[14],"are":[15],"still":[16],"challenging":[17],"for":[18],"downstream":[19],"automatic":[20],"recognition":[22],"(ASR)":[23],"tasks,":[24],"even":[25],"with":[26,151],"satisfactory":[27],"improvements":[28],"in":[29,42,120],"enhancing":[30],"quality":[32],"and":[33,74,95,123,137,144],"intelligibility.":[34],"Recently,":[35],"transformer-based":[36,52],"models":[37],"have":[38],"shown":[39],"better":[40],"performance":[41,134,146],"processing":[44],"tasks.":[45],"Therefore,":[46],"we":[47],"intend":[48],"explore":[50],"a":[51,59,67,76],"SE":[53,72,86,94,122,136,154],"model,":[54],"which":[55,107],"is":[56,64,81,147],"fine-tuned":[57],"through":[58,71,93],"two-stage":[60],"training":[61],"scheme.":[62],"Pre-training":[63],"performed":[65],"using":[66,88],"feature-level":[68],"optimization":[69,91],"criterion":[70,92],"loss,":[73],"then":[75],"pre-trained":[77],"end-to-end":[78],"ASR":[79,96,124,138],"model":[80,87],"used":[82],"fine-tune":[84],"an":[89],"ASR-oriented":[90],"losses.":[97],"We":[98],"evaluate":[99],"proposed":[101],"approach":[102],"on":[103],"low-resourced":[104],"Bengali":[105],"language,":[106],"has":[108],"not":[109],"received":[110],"as":[111,114],"much":[112],"attention":[113],"resource-rich":[115],"English":[116],"or":[117],"Mandarin":[118],"languages":[119],"both":[121],"fields.":[125],"Experimental":[126],"results":[127],"show":[128],"that":[129],"it":[130],"can":[131],"improve":[132],"under":[139],"severe":[140],"unseen":[141],"noisy":[142],"conditions":[143],"its":[145],"reasonably":[148],"good":[149],"compared":[150],"other":[152],"state-of-the-art":[153],"methods.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
