{"id":"https://openalex.org/W4224925070","doi":"https://doi.org/10.1109/icassp43922.2022.9747177","title":"Speech Enhancement with Neural Homomorphic Synthesis","display_name":"Speech Enhancement with Neural Homomorphic Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925070","doi":"https://doi.org/10.1109/icassp43922.2022.9747177"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747177","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101900435","display_name":"Wenbin Jiang","orcid":"https://orcid.org/0000-0002-4063-8952"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenbin Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425934","display_name":"Zhijun Liu","orcid":"https://orcid.org/0000-0002-9386-7441"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034251794","display_name":"Fei Wen","orcid":"https://orcid.org/0000-0002-3083-9611"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101900435"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.3376,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8268262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"380"},"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":0.9994000196456909,"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":0.9952999949455261,"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":0.7828295230865479},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7642256617546082},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.7084720730781555},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6775017380714417},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6708652377128601},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6581634879112244},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.572394847869873},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4836643636226654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4689200520515442},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46734219789505005},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4385855793952942},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.42144882678985596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33607417345046997},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.22586485743522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828295230865479},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7642256617546082},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7084720730781555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6775017380714417},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6708652377128601},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6581634879112244},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.572394847869873},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4836643636226654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4689200520515442},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46734219789505005},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4385855793952942},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.42144882678985596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33607417345046997},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22586485743522644},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747177","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1604034532","https://openalex.org/W2027701650","https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2146324387","https://openalex.org/W2291877678","https://openalex.org/W2516001803","https://openalex.org/W2889442120","https://openalex.org/W2891759647","https://openalex.org/W2930648092","https://openalex.org/W2940275453","https://openalex.org/W2949756029","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963300588","https://openalex.org/W2963341071","https://openalex.org/W2964243274","https://openalex.org/W3000389243","https://openalex.org/W3015626488","https://openalex.org/W3023846453","https://openalex.org/W3095048608","https://openalex.org/W3096408984","https://openalex.org/W3096429957","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3151851237","https://openalex.org/W3162315798","https://openalex.org/W4232282348","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6662018355","https://openalex.org/W6662305780","https://openalex.org/W6696676114","https://openalex.org/W6735429107","https://openalex.org/W6738884980","https://openalex.org/W6757632829","https://openalex.org/W6771763809"],"related_works":["https://openalex.org/W1482212662","https://openalex.org/W3016109656","https://openalex.org/W2100012411","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W1997579527","https://openalex.org/W3135613579","https://openalex.org/W3209446892","https://openalex.org/W2345688450","https://openalex.org/W4386746628"],"abstract_inverted_index":{"Most":[0],"deep":[1],"learning-based":[2],"speech":[3,21,28,37,71,102],"enhancement":[4,29],"methods":[5,117],"operate":[6],"directly":[7],"on":[8,32],"time-frequency":[9],"representations":[10],"or":[11],"learned":[12],"features":[13],"without":[14],"making":[15],"use":[16],"of":[17,20,64,120],"the":[18,60,65,69,76,91,98,108],"model":[19],"production.":[22],"This":[23],"work":[24],"proposes":[25],"a":[26],"new":[27],"method":[30,110],"based":[31],"neural":[33,54,115],"homomorphic":[34],"synthesis.":[35],"The":[36],"signal":[38,72],"is":[39,73],"firstly":[40],"decomposed":[41,66],"into":[42],"excitation":[43,78],"and":[44,79,88,123],"vocal":[45,80],"tract":[46],"with":[47],"complex":[48,62],"cepstrum":[49],"analysis.":[50],"Then,":[51],"two":[52],"complex-valued":[53,114],"networks":[55],"are":[56],"applied":[57],"to":[58],"estimate":[59],"target":[61],"spectrum":[63],"components.":[67],"Finally,":[68],"time-domain":[70],"synthesized":[74],"from":[75],"estimated":[77],"tract.":[81],"Furthermore,":[82],"we":[83],"investigated":[84],"numerous":[85],"loss":[86],"functions":[87],"found":[89],"that":[90,107],"multi-resolution":[92],"STFT":[93],"loss,":[94],"commonly":[95],"used":[96],"in":[97,118],"TTS":[99],"vocoder,":[100],"benefits":[101],"enhancement.":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"proposed":[109],"outperforms":[111],"existing":[112],"state-of-the-art":[113],"network-based":[116],"terms":[119],"both":[121],"PESQ":[122],"eSTOI.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}