{"id":"https://openalex.org/W1544785557","doi":"https://doi.org/10.1109/icassp.2015.7177943","title":"Exploring multi-channel features for denoising-autoencoder-based speech enhancement","display_name":"Exploring multi-channel features for denoising-autoencoder-based speech enhancement","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1544785557","doi":"https://doi.org/10.1109/icassp.2015.7177943","mag":"1544785557"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7177943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Department of Media Science, Nagoya University 1 Furo-cho Chikusa-ku, Nagoya-shi, Aichi, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Media Science, Nagoya University 1 Furo-cho Chikusa-ku, Nagoya-shi, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101685454","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0003-0452-9844"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Department of Media Science, Nagoya University 1 Furo-cho Chikusa-ku, Nagoya-shi, Aichi, Japan","Department of Media Science, Nagoya University, 1 Furo-cho, Chikusa-ku, Nagoya-shi, Aichi 464-0814, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Media Science, Nagoya University 1 Furo-cho Chikusa-ku, Nagoya-shi, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Department of Media Science, Nagoya University, 1 Furo-cho, Chikusa-ku, Nagoya-shi, Aichi 464-0814, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"120"},"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":0.9972000122070312,"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/monaural","display_name":"Monaural","score":0.8104827404022217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7677327394485474},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.766444742679596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7022621631622314},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6551169157028198},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.59779292345047},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5766711831092834},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5475651621818542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44478708505630493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40178316831588745},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3899398446083069},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11338019371032715}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8104827404022217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677327394485474},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.766444742679596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7022621631622314},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6551169157028198},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.59779292345047},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5766711831092834},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5475651621818542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44478708505630493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40178316831588745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3899398446083069},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11338019371032715},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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":1,"locations":[{"id":"doi:10.1109/icassp.2015.7177943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W285277413","https://openalex.org/W1931312565","https://openalex.org/W1973669708","https://openalex.org/W1973681148","https://openalex.org/W1981617403","https://openalex.org/W1985368711","https://openalex.org/W1987906574","https://openalex.org/W1991176864","https://openalex.org/W2018205510","https://openalex.org/W2025768430","https://openalex.org/W2031583051","https://openalex.org/W2031647436","https://openalex.org/W2042071805","https://openalex.org/W2042141988","https://openalex.org/W2062164080","https://openalex.org/W2070707809","https://openalex.org/W2138939691","https://openalex.org/W2144786298","https://openalex.org/W2145094598","https://openalex.org/W2168379380","https://openalex.org/W2290318471","https://openalex.org/W2394967684","https://openalex.org/W2403563897","https://openalex.org/W2997574889","https://openalex.org/W4249052411","https://openalex.org/W6657028776","https://openalex.org/W6680324615","https://openalex.org/W6681096077","https://openalex.org/W6696830301","https://openalex.org/W6711908631"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W3037110488","https://openalex.org/W2538939196"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"a":[3,93,97],"multi-channel":[4,38,55,71,79,89],"denoising":[5],"autoencoder":[6],"(DAE)-based":[7],"speech":[8,19,24,39,100],"enhancement":[9,20,40,101],"approach.":[10],"In":[11,62],"recent":[12],"years,":[13],"deep":[14],"neural":[15],"network":[16],"(DNN)-based":[17],"monaural":[18,94],"and":[21,96],"robust":[22],"automatic":[23],"recognition":[25],"(ASR)":[26],"approaches":[27],"have":[28],"attracted":[29],"much":[30],"attention":[31],"due":[32],"to":[33,76],"their":[34],"high":[35],"performance.":[36,83],"Although":[37],"usually":[41],"outperforms":[42],"single":[43],"channel":[44],"approaches,":[45],"there":[46],"has":[47],"been":[48],"little":[49],"research":[50],"on":[51],"the":[52,58,67],"use":[53,68],"of":[54,60,69],"processing":[56],"in":[57],"context":[59],"DAE.":[61],"this":[63],"paper,":[64],"we":[65],"explore":[66],"several":[70],"features":[72,90],"as":[73],"DAE":[74,95],"input":[75],"confirm":[77],"whether":[78],"information":[80],"can":[81],"improve":[82],"Experimental":[84],"results":[85],"show":[86],"that":[87],"certain":[88],"outperform":[91],"both":[92],"conventional":[98],"time-frequency-mask-based":[99],"method.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}