{"id":"https://openalex.org/W2294333436","doi":"https://doi.org/10.1109/icce.2016.7430657","title":"Multi-stage speech enhancement for automatic speech recognition","display_name":"Multi-stage speech enhancement for automatic speech recognition","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2294333436","doi":"https://doi.org/10.1109/icce.2016.7430657","mag":"2294333436"},"language":"en","primary_location":{"id":"doi:10.1109/icce.2016.7430657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce.2016.7430657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Consumer Electronics (ICCE)","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/A5091044507","display_name":"Seungyeol Lee","orcid":"https://orcid.org/0000-0002-0175-1389"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungyeol Lee","raw_affiliation_strings":["Samsung Electronics, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640170","display_name":"Youngwoo Lee","orcid":"https://orcid.org/0000-0001-6432-3528"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngwoo Lee","raw_affiliation_strings":["Samsung Electronics, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066928377","display_name":"Namgook Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namgook Cho","raw_affiliation_strings":["Samsung Electronics, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics, Suwon, Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5105,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62052184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"384"},"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":0.9973000288009644,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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/speech-enhancement","display_name":"Speech enhancement","score":0.84152752161026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8038224577903748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.776644766330719},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7562684416770935},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5548068284988403},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5152466893196106},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47944536805152893},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.4583025276660919},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4497532248497009},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4370061159133911},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4148717522621155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3420805037021637},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3302701413631439},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10345146059989929},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.058022886514663696}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.84152752161026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038224577903748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.776644766330719},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7562684416770935},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5548068284988403},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5152466893196106},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47944536805152893},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4583025276660919},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4497532248497009},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4370061159133911},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4148717522621155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3420805037021637},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3302701413631439},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10345146059989929},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.058022886514663696}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce.2016.7430657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce.2016.7430657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1851675933","https://openalex.org/W2069486713","https://openalex.org/W2101042021","https://openalex.org/W2127292597","https://openalex.org/W2168729028","https://openalex.org/W2399879654","https://openalex.org/W6639061244","https://openalex.org/W6712652785"],"related_works":["https://openalex.org/W4319347033","https://openalex.org/W2020464095","https://openalex.org/W2341426843","https://openalex.org/W1890431648","https://openalex.org/W1572861854","https://openalex.org/W1968776176","https://openalex.org/W1911859126","https://openalex.org/W1542588102","https://openalex.org/W1987001738","https://openalex.org/W2131711534"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,15],"multi-stage":[6,82],"speech":[7,11,17,27,35,47,59,67,83],"enhancement":[8,18,36,68,84],"technique":[9,77],"for":[10],"recognition.":[12],"At":[13],"first,":[14],"multi-channel":[16],"method":[19,53],"takes":[20],"advantage":[21,64],"of":[22,26,46,58,65],"the":[23,31,56,63,75],"spatial":[24],"information":[25],"source.":[28],"Then,":[29],"in":[30],"second":[32],"stage,":[33],"single-channel":[34],"based":[37],"on":[38],"data-driven":[39],"approach":[40],"is":[41,78],"adopted":[42],"to":[43,80],"improve":[44,55],"performance":[45],"recognition":[48],"at":[49],"server":[50],"side.":[51],"This":[52],"can":[54],"quality":[57],"signal":[60],"which":[61],"maximizes":[62],"each":[66],"technique.":[69],"The":[70],"experimental":[71],"result":[72],"shows":[73],"that":[74],"proposed":[76],"superior":[79],"conventional":[81],"algorithms.":[85]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}