{"id":"https://openalex.org/W2620437712","doi":"https://doi.org/10.1109/icassp.2017.7953081","title":"Improved cepstra minimum-mean-square-error noise reduction algorithm for robust speech recognition","display_name":"Improved cepstra minimum-mean-square-error noise reduction algorithm for robust speech recognition","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2620437712","doi":"https://doi.org/10.1109/icassp.2017.7953081","mag":"2620437712"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, U.S.A","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764456","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-0575-0156"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, U.S.A","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, U.S.A","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100365053"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.7801,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78736264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"4865","last_page":"4869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.7175127863883972},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5880262851715088},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5430478453636169},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5349057912826538},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5325920581817627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5253443121910095},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5173975229263306},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48219409584999084},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4812743067741394},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4796338677406311},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4587670862674713},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44335848093032837},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.43477579951286316},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4324425458908081},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41848549246788025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36196935176849365},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13198769092559814},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13058939576148987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11790922284126282},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11213558912277222},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09328687191009521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175127863883972},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5880262851715088},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5430478453636169},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5349057912826538},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5325920581817627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253443121910095},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5173975229263306},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48219409584999084},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4812743067741394},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4796338677406311},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4587670862674713},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44335848093032837},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.43477579951286316},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4324425458908081},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41848549246788025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36196935176849365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13198769092559814},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13058939576148987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11790922284126282},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11213558912277222},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09328687191009521},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/icassp.2017.7953081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W1480544121","https://openalex.org/W1553154706","https://openalex.org/W1984541135","https://openalex.org/W1992475611","https://openalex.org/W2062164080","https://openalex.org/W2064675550","https://openalex.org/W2076794394","https://openalex.org/W2080921589","https://openalex.org/W2115086266","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2146324387","https://openalex.org/W2147768505","https://openalex.org/W2151484683","https://openalex.org/W2157590573","https://openalex.org/W2160815625","https://openalex.org/W2169147844","https://openalex.org/W2289394825","https://openalex.org/W2293634267","https://openalex.org/W2296748324","https://openalex.org/W2396384435","https://openalex.org/W2408592723","https://openalex.org/W2490695385","https://openalex.org/W2963399332","https://openalex.org/W2964138484","https://openalex.org/W2966212213","https://openalex.org/W3112742522","https://openalex.org/W3147539069","https://openalex.org/W4256112632","https://openalex.org/W6608710415","https://openalex.org/W6677416784","https://openalex.org/W6696934422","https://openalex.org/W6697318756","https://openalex.org/W6713796627","https://openalex.org/W6766224279","https://openalex.org/W6766475400","https://openalex.org/W6787533431","https://openalex.org/W7034522702"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W3125766170","https://openalex.org/W2040641410"],"abstract_inverted_index":{"In":[0,54],"the":[1,29,60,116,158,163],"era":[2],"of":[3,32,157,165],"deep":[4,25,33,69,138],"learning,":[5],"although":[6],"beam-forming":[7],"multi-channel":[8],"signal":[9],"processing":[10],"is":[11,64,76,113,150,154],"still":[12,65],"very":[13,66],"helpful,":[14],"it":[15,75],"was":[16],"reported":[17],"that":[18,41,59,152],"single-channel":[19,61],"robust":[20,62,82],"front-ends":[21],"usually":[22],"cannot":[23],"benefit":[24],"learning":[26,34,70],"models":[27,35,161],"because":[28],"layer-by-layer":[30],"structure":[31],"provides":[36],"a":[37,81,125],"feature":[38],"extraction":[39],"strategy":[40],"automatically":[42],"derives":[43],"powerful":[44],"noise-resistant":[45],"features":[46],"from":[47],"primitive":[48],"raw":[49],"data":[50],"for":[51],"senone":[52],"classification.":[53],"this":[55],"study,":[56],"we":[57],"show":[58],"front-end":[63],"beneficial":[67],"to":[68,177,187],"modelling":[71],"as":[72,74],"long":[73,142],"well":[77],"designed.":[78],"We":[79],"improve":[80],"front-end,":[83,109],"cepstra":[84],"minimum":[85],"mean":[86],"square":[87],"error":[88],"(CMMSE),":[89],"by":[90],"using":[91,133],"more":[92],"reliable":[93],"voice":[94],"activity":[95],"detector,":[96],"refined":[97],"prior":[98],"SNR":[99],"estimation,":[100],"better":[101],"gain":[102],"smoothing":[103],"and":[104,120,124,141,162,185],"two-stage":[105],"processing.":[106],"This":[107],"new":[108],"improved":[110],"CMMSE":[111],"(ICMMSE),":[112],"evaluated":[114],"on":[115,173,182,192],"standard":[117],"Aurora":[118,174],"2":[119],"Chime":[121,183],"3":[122],"tasks,":[123,167],"3400":[126],"hour":[127],"Microsoft":[128],"Cortana":[129,193],"digital":[130,194],"assistant":[131,195],"task":[132],"Gaussian":[134],"mixture":[135],"models,":[136],"feed-forward":[137],"neural":[139,146],"networks,":[140,147],"short-term":[143],"memory":[144],"recurrent":[145],"respectively.":[148,197],"It":[149],"shown":[151],"ICMMSE":[153],"superior":[155],"regardless":[156],"underlying":[159],"acoustic":[160],"scale":[164],"evaluation":[166],"with":[168],"25.46%":[169],"relative":[170,179,189],"WER":[171,180,190],"reduction":[172,181,191],"2,":[175],"up":[176,186],"11.98%":[178],"3,":[184],"11.01%":[188],"task,":[196]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}