{"id":"https://openalex.org/W3198648980","doi":"https://doi.org/10.1109/taslp.2021.3107617","title":"Recurrent Neural Networks and Acoustic Features for Frame-Level Signal-to-Noise Ratio Estimation","display_name":"Recurrent Neural Networks and Acoustic Features for Frame-Level Signal-to-Noise Ratio Estimation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198648980","doi":"https://doi.org/10.1109/taslp.2021.3107617","mag":"3198648980"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3107617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3107617","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100348614","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-5963-4505"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Huhhot, China, 010020 (e-mail: lihao@mail.imu.edu.cn)","Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-5963-4505","affiliations":[{"raw_affiliation_string":"Huhhot, China, 010020 (e-mail: lihao@mail.imu.edu.cn)","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","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":["Computer Science & Engineering, Ohio State University, Columbus, Ohio, United States, 43210 (e-mail: dwang@cse.ohio-state.edu)","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Ohio State University, Columbus, Ohio, United States, 43210 (e-mail: dwang@cse.ohio-state.edu)","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, China, 010021 (e-mail: cszxl@imu.edu.cn)","Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-0406-1105","affiliations":[{"raw_affiliation_string":"Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, China, 010021 (e-mail: cszxl@imu.edu.cn)","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Huhhot, Inner Mongolia, China, (e-mail: csggl@imu.edu.cn)","Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Huhhot, Inner Mongolia, China, (e-mail: csggl@imu.edu.cn)","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.048,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76624731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"29","issue":null,"first_page":"2878","last_page":"2887"},"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":0.9995999932289124,"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":0.9983999729156494,"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":0.7306937575340271},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6738337874412537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6100950837135315},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5834566950798035},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5610475540161133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5439938306808472},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5230263471603394},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.522809624671936},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.48619145154953003},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.467540442943573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4405776262283325},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41594868898391724},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4142375886440277},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34875649213790894},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2986299991607666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18092289566993713},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13591080904006958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306937575340271},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6738337874412537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6100950837135315},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5834566950798035},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5610475540161133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5439938306808472},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5230263471603394},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.522809624671936},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.48619145154953003},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.467540442943573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4405776262283325},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41594868898391724},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4142375886440277},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34875649213790894},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2986299991607666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18092289566993713},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13591080904006958},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3107617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3107617","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G3070352347","display_name":null,"funder_award_id":"61773224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3196667431","display_name":"\u9762\u5411\u8499\u53e4\u8bed\u60c5\u611f\u8bed\u97f3\u5408\u6210\u7684\u8a00\u8bed\u60c5\u611f\u4e0e\u58f0\u5b66\u5efa\u6a21\u7814\u7a76","funder_award_id":"62066033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"},{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W67398352","https://openalex.org/W118588063","https://openalex.org/W1522301498","https://openalex.org/W1574170747","https://openalex.org/W1897240248","https://openalex.org/W1963970749","https://openalex.org/W1964509438","https://openalex.org/W1974387177","https://openalex.org/W1983108229","https://openalex.org/W1986225048","https://openalex.org/W1989364685","https://openalex.org/W1990449877","https://openalex.org/W1990934990","https://openalex.org/W2017608047","https://openalex.org/W2020438552","https://openalex.org/W2024490156","https://openalex.org/W2069681747","https://openalex.org/W2079918934","https://openalex.org/W2090861223","https://openalex.org/W2094461119","https://openalex.org/W2102346872","https://openalex.org/W2104862701","https://openalex.org/W2121973264","https://openalex.org/W2137075158","https://openalex.org/W2138019504","https://openalex.org/W2140977001","https://openalex.org/W2153119843","https://openalex.org/W2153384885","https://openalex.org/W2166529462","https://openalex.org/W2326699523","https://openalex.org/W2516342150","https://openalex.org/W2516547830","https://openalex.org/W2529545010","https://openalex.org/W2598036111","https://openalex.org/W2607288499","https://openalex.org/W2678916739","https://openalex.org/W2746179223","https://openalex.org/W2807396610","https://openalex.org/W2890401420","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W3049430014","https://openalex.org/W3095173690","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4232282348","https://openalex.org/W6631190155","https://openalex.org/W6675700563","https://openalex.org/W6784413683","https://openalex.org/W6917638038","https://openalex.org/W6981674109"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2118992737"],"abstract_inverted_index":{"It":[0],"is":[1],"important":[2],"to":[3,86,117],"know":[4],"the":[5,8,126],"presence":[6],"and":[7,34,99,106],"relative":[9],"level":[10,29],"of":[11,26,30,57,96,133],"background":[12],"noise":[13,28,143],"for":[14,40,69],"many":[15],"speech":[16],"processing":[17],"tasks.":[18],"Frame-level":[19],"signal-to-noise":[20],"ratio":[21],"(SNR)":[22],"provides":[23,129],"a":[24,31,48,65,94],"measure":[25],"instantaneous":[27],"noisy":[32,58],"signal,":[33],"its":[35],"estimation":[36],"has":[37],"been":[38],"researched":[39],"decades.":[41],"This":[42],"problem":[43],"can":[44],"be":[45],"approached":[46],"from":[47,55],"supervised":[49],"learning":[50,67],"perspective":[51],"by":[52],"predicting":[53],"SNR":[54,71,120],"features":[56,98],"speech.":[59],"In":[60],"this":[61],"study,":[62],"we":[63],"introduce":[64],"deep":[66],"algorithm":[68,75,114,128],"frame-level":[70,134],"estimation.":[72],"The":[73,112],"proposed":[74,113,127],"employs":[76],"recurrent":[77],"neural":[78],"networks":[79],"(RNNs)":[80],"with":[81],"long":[82],"short-term":[83],"memory":[84],"(LSTM)":[85],"leverage":[87],"contextual":[88],"information.":[89],"We":[90],"also":[91],"systematically":[92],"examine":[93],"range":[95],"acoustic":[97],"investigate":[100],"feature":[101],"combinations":[102],"using":[103],"Group":[104],"Lasso":[105],"sequential":[107],"floating":[108],"forward":[109],"selection":[110],"(SFFS).":[111],"naturally":[115],"leads":[116],"an":[118,130],"utterance-level":[119,139],"estimator.":[121],"Systematical":[122],"evaluations":[123],"show":[124],"that":[125],"accurate":[131],"estimate":[132],"SNR,":[135,140],"as":[136,138],"well":[137],"under":[141],"different":[142],"conditions,":[144],"outperforming":[145],"other":[146],"estimators.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}