{"id":"https://openalex.org/W3130352849","doi":"https://doi.org/10.1109/icassp39728.2021.9414965","title":"A Modulation-Domain Loss for Neural-Network-Based Real-Time Speech Enhancement","display_name":"A Modulation-Domain Loss for Neural-Network-Based Real-Time Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3130352849","doi":"https://doi.org/10.1109/icassp39728.2021.9414965","mag":"3130352849"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.07330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109404932","display_name":"Tyler Vuong","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler Vuong","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104037412","display_name":"Yangyang Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangyang Xia","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069424860","display_name":"Richard M. Stern","orcid":"https://orcid.org/0000-0003-0557-7282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard M. Stern","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109404932"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3084,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51083757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6643","last_page":"6647"},"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":0.9976999759674072,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7194134593009949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6993381977081299},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6948559880256653},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6689355373382568},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.5854395627975464},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5375378727912903},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5137091875076294},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5126637816429138},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.477867066860199},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4503322243690491},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44437074661254883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4344441890716553},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.42798006534576416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22745242714881897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1575799286365509},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07632848620414734},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07104793190956116},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07091432809829712}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7194134593009949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993381977081299},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6948559880256653},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6689355373382568},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.5854395627975464},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5375378727912903},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5137091875076294},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5126637816429138},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.477867066860199},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4503322243690491},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44437074661254883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4344441890716553},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.42798006534576416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22745242714881897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1575799286365509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07632848620414734},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07104793190956116},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07091432809829712},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.07330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07330","pdf_url":"https://arxiv.org/pdf/2102.07330","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3130352849","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.07330","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.07330","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.07330","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/29h3-f783","is_oa":true,"landing_page_url":"https://doi.org/10.17023/29h3-f783","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.07330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07330","pdf_url":"https://arxiv.org/pdf/2102.07330","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130352849.pdf","grobid_xml":"https://content.openalex.org/works/W3130352849.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1968939597","https://openalex.org/W1987831012","https://openalex.org/W1989034586","https://openalex.org/W1994139191","https://openalex.org/W2017369438","https://openalex.org/W2027890689","https://openalex.org/W2054139811","https://openalex.org/W2066447739","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2072873503","https://openalex.org/W2118640610","https://openalex.org/W2121973264","https://openalex.org/W2130426352","https://openalex.org/W2142709321","https://openalex.org/W2603567530","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2952218014","https://openalex.org/W2991015288","https://openalex.org/W3002439978","https://openalex.org/W3013020904","https://openalex.org/W3016120385","https://openalex.org/W3084645150","https://openalex.org/W3088490496","https://openalex.org/W3092967725","https://openalex.org/W3097034112","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W6772622344","https://openalex.org/W6773903951","https://openalex.org/W6782481672","https://openalex.org/W6783634143"],"related_works":["https://openalex.org/W3088775906","https://openalex.org/W2946277146","https://openalex.org/W2915844545","https://openalex.org/W2736138094","https://openalex.org/W3108010525","https://openalex.org/W2943554574","https://openalex.org/W2892110446","https://openalex.org/W3108487808","https://openalex.org/W3011129471","https://openalex.org/W2363736995","https://openalex.org/W2465697055","https://openalex.org/W3103003256","https://openalex.org/W2564013664","https://openalex.org/W3132918556","https://openalex.org/W2740916758","https://openalex.org/W2605589342","https://openalex.org/W3174609245","https://openalex.org/W3015592506","https://openalex.org/W2808920027","https://openalex.org/W2778338786"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,21,33,44],"modulation-domain":[3,53],"loss":[4],"function":[5],"for":[6,20,42,72],"deep-learning-based":[7],"speech":[8,45,68,74],"enhancement":[9,46,75],"systems.":[10],"Learnable":[11],"spectro-temporal":[12,60],"receptive":[13],"fields":[14],"(STRFs)":[15],"were":[16,28],"adapted":[17],"to":[18,31,55],"optimize":[19],"speaker":[22],"identification":[23],"task.":[24],"The":[25],"learned":[26],"STRFs":[27],"then":[29],"used":[30],"calculate":[32],"weighted":[34],"mean-squared":[35],"error":[36],"(MSE)":[37],"in":[38,58],"the":[39,52,56,59,64],"modulation":[40],"domain":[41,61],"training":[43],"system.":[47],"Experiments":[48],"showed":[49],"that":[50],"adding":[51],"MSE":[54,57],"substantially":[62],"improved":[63],"objective":[65],"prediction":[66],"of":[67],"quality":[69],"and":[70],"intelligibility":[71],"real-time":[73],"systems":[76],"without":[77],"incurring":[78],"additional":[79],"computation":[80],"during":[81],"inference.":[82]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}