{"id":"https://openalex.org/W2408688265","doi":"https://doi.org/10.21437/interspeech.2015-409","title":"Text-informed speech enhancement with deep neural networks","display_name":"Text-informed speech enhancement with deep neural networks","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2408688265","doi":"https://doi.org/10.21437/interspeech.2015-409","mag":"2408688265"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-409","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1760","last_page":"1764"},"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":0.9995999932289124,"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":0.9965000152587891,"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":0.6577033400535583},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5650573372840881},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4949342608451843},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49353015422821045},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41997015476226807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3894615173339844},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.346139520406723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6577033400535583},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5650573372840881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4949342608451843},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49353015422821045},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41997015476226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3894615173339844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.346139520406723},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-409","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W88864901","https://openalex.org/W1544785557","https://openalex.org/W1665196592","https://openalex.org/W1974186229","https://openalex.org/W2003020982","https://openalex.org/W2007739946","https://openalex.org/W2013608223","https://openalex.org/W2027081853","https://openalex.org/W2042071805","https://openalex.org/W2042141988","https://openalex.org/W2062164080","https://openalex.org/W2078528584","https://openalex.org/W2079623482","https://openalex.org/W2102003408","https://openalex.org/W2111208321","https://openalex.org/W2118415306","https://openalex.org/W2124149378","https://openalex.org/W2144786298","https://openalex.org/W2149648698","https://openalex.org/W2150658333","https://openalex.org/W2158291955","https://openalex.org/W2160306971","https://openalex.org/W2290318471","https://openalex.org/W2294797155"],"related_works":["https://openalex.org/W3000194274","https://openalex.org/W4309353705","https://openalex.org/W2077541282","https://openalex.org/W2904687844","https://openalex.org/W2965002127","https://openalex.org/W2952917250","https://openalex.org/W4286800517","https://openalex.org/W2042141988","https://openalex.org/W4297968711","https://openalex.org/W2891182163"],"abstract_inverted_index":{"A":[0],"speech":[1,30,43,95,129,173,185],"signal":[2,91,136],"captured":[3],"by":[4,11,51,73,131,175],"a":[5,41,57],"distant":[6],"microphone":[7],"is":[8,49,71],"generally":[9],"contaminated":[10],"background":[12,153],"noise,":[13],"which":[14,97],"severely":[15],"degrades":[16],"the":[17,23,46,52,61,74,78,93,101,108,123,127,134,143,152,155,158,165,180],"audible":[18],"quality":[19],"and":[20,137,154,178],"intelligibility":[21],"of":[22,60,92,107,110,157],"observed":[24,135],"signal.":[25],"To":[26],"resolve":[27],"this":[28,37,147],"issue,":[29],"enhancement":[31,47,96,174,181],"has":[32],"been":[33],"intensively":[34],"studied.":[35],"In":[36,146],"paper,":[38,148],"we":[39,149,162],"consider":[40],"text-informed":[42],"enhancement,":[44,186],"where":[45],"process":[48],"guided":[50],"corresponding":[53,144],"text":[54,166],"information,":[55],"i.e.,":[56],"correct":[58],"transcription":[59],"target":[62],"utterance.":[63],"The":[64],"proposed":[65,124,159],"deep":[66,188],"neural":[67,189],"network":[68,190],"(DNN)based":[69],"framework":[70],"motivated":[72],"recent":[75],"success":[76],"in":[77,82,119],"textto-speech":[79],"(TTS)":[80],"research":[81,103],"employing":[83],"DNN":[84,111,177],"as":[85,87],"well":[86],"high":[88],"audible-quality":[89],"output":[90],"corpus-based":[94],"borrows":[98],"knowledge":[99],"from":[100,142],"TTS":[102,139],"field.":[104],"Taking":[105],"advantage":[106],"nature":[109],"that":[112],"allows":[113],"us":[114],"to":[115],"utilize":[116],"disparate":[117],"features":[118,130,140],"an":[120],"inference":[121],"stage,":[122],"method":[125],"infers":[126],"clean":[128],"jointly":[132],"using":[133],"widely-used":[138],"derived":[141],"text.":[145],"first":[150],"introduce":[151],"details":[156],"method.":[160],"Then,":[161],"show":[163],"how":[164],"information":[167],"can":[168],"be":[169],"naturally":[170],"integrated":[171],"into":[172],"utilizing":[176],"improve":[179],"performance.":[182],"Index":[183],"Terms:":[184],"text-to-speech,":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}