{"id":"https://openalex.org/W2536160108","doi":"https://doi.org/10.1109/iwaenc.2016.7602943","title":"A phoneme-based pre-training approach for deep neural network with application to speech enhancement","display_name":"A phoneme-based pre-training approach for deep neural network with application to speech enhancement","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2536160108","doi":"https://doi.org/10.1109/iwaenc.2016.7602943","mag":"2536160108"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2016.7602943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2016.7602943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5080213609","display_name":"Shlomo E. Chazan","orcid":"https://orcid.org/0000-0002-6614-6112"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Shlomo E. Chazan","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005409420","display_name":"Jacob Goldberger","orcid":"https://orcid.org/0000-0002-2225-1914"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Goldberger","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080213609"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":4.2871,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9521853,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9980000257492065,"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":0.9961000084877014,"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":0.7535690069198608},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.732426643371582},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5916911959648132},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5669457316398621},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5245554447174072},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4649791419506073},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4487447440624237},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43474695086479187},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4214699864387512},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38929301500320435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3883898854255676},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1344943642616272},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.09502795338630676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7535690069198608},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.732426643371582},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5916911959648132},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5669457316398621},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5245554447174072},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4649791419506073},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4487447440624237},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43474695086479187},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4214699864387512},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38929301500320435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3883898854255676},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1344943642616272},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.09502795338630676},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc.2016.7602943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2016.7602943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1920160043","https://openalex.org/W1974387177","https://openalex.org/W1992475611","https://openalex.org/W2027701650","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2086139506","https://openalex.org/W2095705004","https://openalex.org/W2103135337","https://openalex.org/W2110798204","https://openalex.org/W2111070087","https://openalex.org/W2130322773","https://openalex.org/W2136922672","https://openalex.org/W2144404214","https://openalex.org/W2168379380","https://openalex.org/W2168793898","https://openalex.org/W2236045036","https://openalex.org/W2398264106","https://openalex.org/W2405774341","https://openalex.org/W3127686677","https://openalex.org/W6674330103","https://openalex.org/W6676481782","https://openalex.org/W6684458083","https://openalex.org/W6689820921"],"related_works":["https://openalex.org/W3016163030","https://openalex.org/W1978861297","https://openalex.org/W2564061992","https://openalex.org/W2418631473","https://openalex.org/W2103878314","https://openalex.org/W36799504","https://openalex.org/W1598166535","https://openalex.org/W2485008119","https://openalex.org/W2105971979","https://openalex.org/W2112089769"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"present":[4],"a":[5,35,62,73,88,124],"new":[6,184],"phoneme-based":[7],"deep":[8],"neural":[9],"network":[10,157],"(DNN)":[11],"framework":[12,33],"for":[13,42,56],"single":[14],"microphone":[15],"speech":[16,20,29,75,80,119,190],"enhancement.":[17,191],"While":[18],"most":[19],"enhancement":[21],"algorithms":[22],"overlook":[23],"the":[24,28,58,70,92,96,100,110,117,135,139,152,155,162,166,180,183,187,193,204],"phoneme":[25,64,102,136,169,205],"structure":[26,206],"of":[27,37,69,91,173,182,189],"signal,":[30],"our":[31],"proposed":[32,194],"comprises":[34],"set":[36],"phoneme-specific":[38,74,93],"DNNs":[39],"(pDNNs),":[40],"one":[41],"each":[43,68,129],"phoneme,":[44],"together":[45],"with":[46,95,165],"an":[47],"additional":[48],"phoneme-classification":[49],"DNN":[50],"(cDNN).":[51],"The":[52,79],"cDNN":[53,140,167],"is":[54,84,112,131,141,158],"responsible":[55],"determining":[57],"posterior":[59,101],"probability":[60,77,82],"that":[61,199],"specific":[63],"was":[65],"uttered.":[66],"Concurrently,":[67],"pDNNs":[71],"estimates":[72],"presence":[76,81],"(pSPP).":[78],"(SPP)":[83],"then":[85,113,159],"calculated":[86],"as":[87],"weighted":[89],"averaging":[90],"pSPPs,":[94],"weights":[97],"determined":[98],"by":[99],"probability.":[103],"A":[104,171],"soft":[105],"spectral":[106],"attenuation,":[107],"based":[108],"on":[109],"SPP,":[111],"applied":[114],"to":[115,143,186],"enhance":[116],"noisy":[118,163],"signal.":[120],"We":[121],"further":[122],"propose":[123],"compound":[125],"training":[126,210],"procedure,":[127],"where":[128],"pDNN":[130],"first":[132],"pre-trained":[133],"using":[134,161],"labeling":[137],"and":[138],"trained":[142,160],"classify":[144],"phonemes.":[145],"Since":[146],"these":[147],"labels":[148],"are":[149],"unavailable":[150],"in":[151,175],"test":[153],"phase,":[154],"entire":[156],"utterance,":[164],"providing":[168],"classification.":[170],"series":[172],"experiments":[174],"different":[176],"noise":[177],"types":[178],"verifies":[179],"applicability":[181],"algorithm":[185],"task":[188],"Moreover,":[192],"scheme":[195],"outperforms":[196],"other":[197],"schemes":[198],"either":[200],"do":[201],"not":[202],"consider":[203],"or":[207],"use":[208],"simpler":[209],"methodology.":[211]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}