{"id":"https://openalex.org/W2394573342","doi":"https://doi.org/10.1109/icassp.2016.7472773","title":"Robust speech recognition from ratio masks","display_name":"Robust speech recognition from ratio masks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2394573342","doi":"https://doi.org/10.1109/icassp.2016.7472773","mag":"2394573342"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472773","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 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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.4434,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78408453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2016","issue":null,"first_page":"5720","last_page":"5724"},"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":0.9980999827384949,"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":0.8009825348854065},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7933024168014526},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7177145481109619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7164294719696045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6168862581253052},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5921832323074341},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.589647114276886},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4966731667518616},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4615398049354553},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4559805989265442},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.41657736897468567},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.11396807432174683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09774374961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009825348854065},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7933024168014526},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7177145481109619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7164294719696045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6168862581253052},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5921832323074341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.589647114276886},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4966731667518616},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4615398049354553},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4559805989265442},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.41657736897468567},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11396807432174683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09774374961853027},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472773","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 Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"mag:2750380753","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/201602230197792332","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W84880661","https://openalex.org/W160800111","https://openalex.org/W1989364685","https://openalex.org/W1992475611","https://openalex.org/W2015337779","https://openalex.org/W2029177977","https://openalex.org/W2035576074","https://openalex.org/W2112796928","https://openalex.org/W2126597753","https://openalex.org/W2137075158","https://openalex.org/W2137094732","https://openalex.org/W2141411743","https://openalex.org/W2146871184","https://openalex.org/W2152131029","https://openalex.org/W2163605009","https://openalex.org/W2168379380","https://openalex.org/W2295627154","https://openalex.org/W2396918387","https://openalex.org/W2397728357","https://openalex.org/W2561557072","https://openalex.org/W4233392025","https://openalex.org/W6603374476","https://openalex.org/W6684191040","https://openalex.org/W6697236289","https://openalex.org/W6712395177","https://openalex.org/W6712476441"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W3202613528"],"abstract_inverted_index":{"Robustness":[0],"against":[1],"noise":[2],"is":[3,39,60],"crucial":[4],"for":[5,97],"automatic":[6],"speech":[7],"recognition":[8,82,88],"systems":[9],"in":[10],"real-world":[11],"environments.":[12],"In":[13,30],"this":[14],"paper,":[15],"we":[16],"propose":[17],"a":[18,34,50,55],"novel":[19],"approach":[20,68],"that":[21,80],"performs":[22],"robust":[23,98],"ASR":[24],"by":[25],"directly":[26],"recognizing":[27],"ratio":[28,46,84],"masks.":[29],"the":[31,44,73,77],"proposed":[32,67],"approach,":[33],"deep":[35],"neural":[36,57],"network":[37,58],"(DNN)":[38],"first":[40],"trained":[41],"to":[42,62],"estimate":[43],"ideal":[45],"mask":[47],"(IRM)":[48],"from":[49],"noisy":[51],"utterance":[52],"and":[53,76,92],"then":[54],"convolutional":[56],"(CNN)":[59],"employed":[61],"recognize":[63],"estimated":[64],"IRMs.":[65],"The":[66],"has":[69],"been":[70],"evaluated":[71],"on":[72],"TIDigits":[74],"corpus,":[75],"results":[78],"demonstrate":[79],"direct":[81,87],"of":[83,89],"masks":[85,91],"outperforms":[86],"binary":[90],"traditional":[93],"MMSE-HMM":[94],"based":[95],"method":[96],"ASR.":[99]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}