{"id":"https://openalex.org/W2612890541","doi":"https://doi.org/10.1109/iscslp.2016.7918496","title":"HMM-based cue parameters estimation for speech enhancement","display_name":"HMM-based cue parameters estimation for speech enhancement","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2612890541","doi":"https://doi.org/10.1109/iscslp.2016.7918496","mag":"2612890541"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101374328","display_name":"Feng Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Deng","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang-chun Bao","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000601742","display_name":"Maoshen Jia","orcid":"https://orcid.org/0000-0002-3452-3913"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao-shen Jia","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"1","last_page":"4"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/pesq","display_name":"PESQ","score":0.7337098121643066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322606444358826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7231649160385132},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7042405605316162},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6024430990219116},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5168524384498596},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5114563703536987},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5067856907844543},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.47935420274734497},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44318148493766785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4285619854927063},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41600751876831055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4129462242126465},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2334122359752655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1696992814540863}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7337098121643066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322606444358826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7231649160385132},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7042405605316162},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6024430990219116},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5168524384498596},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5114563703536987},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5067856907844543},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.47935420274734497},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44318148493766785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4285619854927063},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41600751876831055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4129462242126465},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2334122359752655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1696992814540863},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1486632395","https://openalex.org/W1546892833","https://openalex.org/W1974387177","https://openalex.org/W2011057521","https://openalex.org/W2016254085","https://openalex.org/W2025515167","https://openalex.org/W2096044413","https://openalex.org/W2101042021","https://openalex.org/W2115812730","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2159514726","https://openalex.org/W2163195137","https://openalex.org/W2166223512","https://openalex.org/W2169147844","https://openalex.org/W3147539069","https://openalex.org/W6628849183"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W3211091508","https://openalex.org/W2535938215","https://openalex.org/W2015497124","https://openalex.org/W1991337662","https://openalex.org/W72660888"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,106],"hidden":[4],"Markov":[5],"model":[6],"(HMM)-based":[7],"cue":[8,21,25,87,91,98,112,117,126,130,145],"parameters":[9,22,88,92,113,118,131],"estimation":[10],"method":[11,175],"for":[12,119,152,161],"single-channel":[13,31],"speech":[14,32,39,58,73,82,120,136,148],"enhancement":[15,33],"is":[16,59,100,150],"proposed,":[17],"in":[18],"which":[19,103],"the":[20,37,46,56,62,71,79,85,97,105,110,115,124,128,140,147,162,166,173,179],"of":[23,51,66,143],"binaural":[24],"coding":[26],"(BCC)":[27],"are":[28,43,93,132],"applied":[29],"to":[30,70],"system":[34],"successfully.":[35],"First,":[36],"clean":[38,72,86,111,129],"and":[40,48,55,74,78,89,114,170],"noise":[41,75],"signals":[42],"considered":[44],"as":[45,61],"left":[47],"right":[49],"channels":[50],"stereo":[52],"signal,":[53],"respectively;":[54],"noisy":[57,81,135,154],"treated":[60],"down-mixed":[63],"mono":[64],"signal":[65],"BCC":[67,144],"method.":[68],"According":[69],"data":[76,83],"set":[77],"corresponding":[80],"set,":[84],"pre-enhanced":[90,116],"extracted,":[94],"respectively.":[95],"Then":[96],"HMM":[99],"trained":[101,125],"offline,":[102],"exploits":[104],"priori":[107],"information":[108],"about":[109],"enhancement.":[121],"Next,":[122],"using":[123],"HMM,":[127],"estimated":[133],"from":[134],"online.":[137],"Finally,":[138],"following":[139],"synthesis":[141],"principle":[142],"parameters,":[146],"estimator":[149],"constructed":[151],"enhancing":[153],"speech.":[155],"The":[156],"test":[157],"results":[158],"demonstrate":[159],"that,":[160],"segmental":[163],"signal-noise-ratio":[164],"(SNR),":[165],"log":[167],"spectral":[168],"distortion":[169],"PESQ":[171],"measures,":[172],"proposed":[174],"performs":[176],"better":[177],"than":[178],"reference":[180],"methods.":[181]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}