{"id":"https://openalex.org/W3007482166","doi":"https://doi.org/10.1109/asru46091.2019.9003987","title":"Improving Speech Enhancement with Phonetic Embedding Features","display_name":"Improving Speech Enhancement with Phonetic Embedding Features","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007482166","doi":"https://doi.org/10.1109/asru46091.2019.9003987","mag":"3007482166"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003987","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100672630","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0002-3126-5103"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Wu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072495935","display_name":"Lianwu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwu Chen","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052541894","display_name":"Mingjie Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Jin","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100672630"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.1659,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48901436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"645","last_page":"651"},"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":0.9969000220298767,"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":0.7905570268630981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7352197170257568},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6102715730667114},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5660309195518494},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5453920960426331},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5270764231681824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4975884258747101},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4549441337585449},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44178518652915955},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4326452612876892},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42725226283073425},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34551364183425903},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06592705845832825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905570268630981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7352197170257568},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6102715730667114},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5660309195518494},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5453920960426331},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5270764231681824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975884258747101},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4549441337585449},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44178518652915955},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4326452612876892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42725226283073425},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34551364183425903},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06592705845832825},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003987","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W258661521","https://openalex.org/W1482149378","https://openalex.org/W1600744878","https://openalex.org/W1897240248","https://openalex.org/W2008971146","https://openalex.org/W2057826000","https://openalex.org/W2067584370","https://openalex.org/W2120933697","https://openalex.org/W2141411743","https://openalex.org/W2144404214","https://openalex.org/W2153849757","https://openalex.org/W2291877678","https://openalex.org/W2408713104","https://openalex.org/W2542605056","https://openalex.org/W2584329820","https://openalex.org/W2755891984","https://openalex.org/W2760287881","https://openalex.org/W2936401635","https://openalex.org/W4245838404","https://openalex.org/W4296927107","https://openalex.org/W6609686331","https://openalex.org/W6713729801","https://openalex.org/W6744261651","https://openalex.org/W6760977771"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W111365173","https://openalex.org/W2386453889","https://openalex.org/W3134790285"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,25,61,135],"speech":[6,34,104,121,132],"enhancement":[7,35,105,128],"framework":[8,97],"that":[9,37,76,94],"leverages":[10],"phonetic":[11,46,79],"information":[12],"obtained":[13],"from":[14],"the":[15,39,53,78,83,95,100,120],"acoustic":[16,74],"model.":[17],"It":[18],"consists":[19],"of":[20,41,86],"two":[21],"separate":[22],"components:":[23],"(i)":[24],"long":[26,63],"short-term":[27,64],"memory":[28,65],"recurrent":[29],"neural":[30,70],"network":[31,71],"(LSTM-RNN)":[32],"based":[33,73],"model":[36,75],"takes":[38],"combination":[40],"log-power":[42],"spectra":[43],"(LPS)":[44],"and":[45,59,66,102,116,133],"embedding":[47],"features":[48],"as":[49],"input":[50],"to":[51,113,119],"predict":[52],"complex":[54],"ideal":[55],"ratio":[56],"mask":[57],"(cIRM);":[58],"(ii)":[60],"convolutional,":[62],"fully":[67],"connected":[68],"deep":[69],"(CLDNN)":[72],"extracts":[77],"feature":[80],"vector":[81],"in":[82],"hidden":[84],"units":[85],"its":[87,126],"LSTM":[88],"layer.":[89],"Our":[90],"experimental":[91],"results":[92],"show":[93],"proposed":[96],"outperforms":[98],"both":[99],"conventional":[101],"phoneme-dependent":[103],"systems":[106],"under":[107],"various":[108],"noisy":[109],"conditions,":[110,115],"generalizes":[111],"well":[112],"unseen":[114],"performs":[117],"robustly":[118],"interference.":[122],"We":[123],"further":[124],"demonstrate":[125],"superior":[127],"performance":[129],"on":[130,141],"unvoiced":[131],"report":[134],"preliminary":[136],"yet":[137],"promising":[138],"recognition":[139],"experiment":[140],"real":[142],"test":[143],"data.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}