{"id":"https://openalex.org/W2292405593","doi":"https://doi.org/10.1109/apsipa.2015.7415289","title":"Music removal by convolutional denoising autoencoder in speech recognition","display_name":"Music removal by convolutional denoising autoencoder in speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2292405593","doi":"https://doi.org/10.1109/apsipa.2015.7415289","mag":"2292405593"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5055086029","display_name":"Mengyuan Zhao","orcid":"https://orcid.org/0000-0002-8917-0780"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mengyuan Zhao","raw_affiliation_strings":["Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391444","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-0747-7042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352615","display_name":"Zhiyong Zhang","orcid":"https://orcid.org/0000-0003-1622-3447"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Zhang","raw_affiliation_strings":["Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100601221","display_name":"Xuewei Zhang","orcid":"https://orcid.org/0000-0002-9098-6461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuewei Zhang","raw_affiliation_strings":["Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technology (CSLT), Tsinghua National Lab for Information Science and Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055086029"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8819,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95912775,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"341"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830760478973389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7568378448486328},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7148139476776123},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5690714716911316},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5644989609718323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5243476033210754},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4927995502948761},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.48123812675476074},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43108034133911133},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4209698736667633},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41567254066467285},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41317975521087646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3752395510673523},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08780121803283691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830760478973389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7568378448486328},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7148139476776123},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5690714716911316},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5644989609718323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5243476033210754},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4927995502948761},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.48123812675476074},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43108034133911133},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4209698736667633},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41567254066467285},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41317975521087646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3752395510673523},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08780121803283691},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W68855703","https://openalex.org/W1604771987","https://openalex.org/W1970714145","https://openalex.org/W1996546547","https://openalex.org/W2022668263","https://openalex.org/W2025768430","https://openalex.org/W2036339641","https://openalex.org/W2096653978","https://openalex.org/W2127982613","https://openalex.org/W2131042651","https://openalex.org/W2132597408","https://openalex.org/W2141040243","https://openalex.org/W2150341604","https://openalex.org/W2160767268","https://openalex.org/W2164098335","https://openalex.org/W2171153836","https://openalex.org/W2290318471","https://openalex.org/W2296581541","https://openalex.org/W2399506744","https://openalex.org/W6635896687","https://openalex.org/W6685455253","https://openalex.org/W6712781682"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W3037110488"],"abstract_inverted_index":{"Music":[0],"embedding":[1],"often":[2],"causes":[3],"significant":[4,71],"performance":[5,72],"degradation":[6],"in":[7,62,95,106],"automatic":[8],"speech":[9,30,105],"recognition":[10],"(ASR).":[11],"This":[12],"paper":[13],"proposes":[14],"a":[15,90],"music-removal":[16,81],"method":[17],"based":[18],"on":[19,35],"denoising":[20,37],"autoencoder":[21,38],"(DAE)":[22],"that":[23,40,53,79,89],"learns":[24],"and":[25,65,109],"removes":[26],"music":[27,61,68,103],"from":[28,104],"music-embedded":[29],"signals.":[31],"Particularly,":[32],"we":[33,77],"focus":[34],"convolutional":[36,47],"(CDAE)":[39],"can":[41,57,98],"learn":[42,58],"local":[43],"musical":[44],"patterns":[45,59],"by":[46],"feature":[48],"extraction.":[49],"Our":[50],"study":[51],"shows":[52],"the":[54,66],"CDAE":[55],"model":[56,91],"of":[60],"different":[63],"genres":[64],"CDAE-based":[67],"removal":[69],"offers":[70],"improvement":[73],"for":[74],"ASR.":[75],"Additionally,":[76],"demonstrate":[78],"this":[80],"approach":[82],"is":[83],"largely":[84],"language":[85,97],"independent,":[86],"which":[87],"means":[88],"trained":[92,111],"with":[93,112],"data":[94,114],"one":[96],"be":[99],"applied":[100],"to":[101,117],"remove":[102],"another":[107],"language,":[108],"models":[110],"multilingual":[113],"may":[115],"lead":[116],"better":[118],"performance.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}