{"id":"https://openalex.org/W2886891848","doi":"https://doi.org/10.21437/interspeech.2018-2321","title":"Denoising and Raw-waveform Networks for Weakly-Supervised Gender Identification on Noisy Speech","display_name":"Denoising and Raw-waveform Networks for Weakly-Supervised Gender Identification on Noisy Speech","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2886891848","doi":"https://doi.org/10.21437/interspeech.2018-2321","mag":"2886891848"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2321","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/256316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074037143","display_name":"Jilt Sebastian","orcid":"https://orcid.org/0000-0002-9780-7745"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH","IN"],"is_corresponding":true,"raw_author_name":"Jilt Sebastian","raw_affiliation_strings":["Idiap Research Institute, Martigny, CH","Indian Institute of Technology Madras, India","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, CH","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849944","display_name":"Manoj Kumar","orcid":"https://orcid.org/0000-0003-2100-461X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manoj Kumar","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032270728","display_name":"D. S. Pavan Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"D. S. Pavan Kumar","raw_affiliation_strings":["Idiap Research Institute, Martigny, CH","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, CH","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, CH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, CH","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hema Murthy","raw_affiliation_strings":["Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074037143"],"corresponding_institution_ids":["https://openalex.org/I24676775","https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.3616,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50301166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"292","last_page":"296"},"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":0.9991999864578247,"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/noise-reduction","display_name":"Noise reduction","score":0.7228379249572754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7218946814537048},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6554200053215027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6293829679489136},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6056872010231018},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5986538529396057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5715097188949585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5581567287445068},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5425049662590027},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5186694860458374},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4479396939277649},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.44720637798309326},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4389571249485016},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.13253998756408691}],"concepts":[{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.7228379249572754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218946814537048},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6554200053215027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6293829679489136},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6056872010231018},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5986538529396057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5715097188949585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5581567287445068},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5425049662590027},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5186694860458374},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4479396939277649},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44720637798309326},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4389571249485016},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.13253998756408691},{"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-2321","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:256316","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256316","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:267014","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/267014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:256316","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256316","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321942","display_name":"Hasler Stiftung","ror":"https://ror.org/04m3t9183"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W247701703","https://openalex.org/W1790748249","https://openalex.org/W1973681148","https://openalex.org/W2044893557","https://openalex.org/W2063125572","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2101234009","https://openalex.org/W2105339405","https://openalex.org/W2125336414","https://openalex.org/W2127851351","https://openalex.org/W2135731872","https://openalex.org/W2161576138","https://openalex.org/W2291299091","https://openalex.org/W2338316711","https://openalex.org/W2399733683","https://openalex.org/W2407277936","https://openalex.org/W2534261280","https://openalex.org/W2734846839","https://openalex.org/W2738359832","https://openalex.org/W2770454110","https://openalex.org/W2887949187","https://openalex.org/W2963175699","https://openalex.org/W4232282348","https://openalex.org/W4297792748"],"related_works":["https://openalex.org/W3108403339","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W4287867034","https://openalex.org/W2175872006","https://openalex.org/W4375869276"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,12,36,54,63,82,92,107],"raw-waveform":[4,108],"neural":[5,110],"network":[6,14,111],"and":[7,42,58,130,142,159,179],"uses":[8],"it":[9],"along":[10],"with":[11,114],"denoising":[13,51,73],"for":[15,90,156],"clustering":[16],"in":[17,66,124,176],"weakly":[18],"supervised":[19],"learning":[20,91],"scenarios":[21],"under":[22],"extreme":[23],"noise":[24,40],"conditions.":[25],"Specifically,":[26],"we":[27],"consider":[28],"language":[29],"independent":[30],"Automatic":[31],"Gender":[32],"Recognition":[33],"(AGR)":[34],"on":[35,81],"set":[37],"of":[38,87,122,126,140],"varied":[39],"conditions":[41],"Signal":[43],"to":[44,68,106],"Noise":[45],"Ratios":[46],"(SNRs).":[47],"We":[48,117,165],"formulate":[49],"the":[50,60,88,119,147,151,168,172],"problem":[52],"as":[53,104],"source":[55],"separation":[56],"task":[57],"train":[59],"system":[61,155],"using":[62],"discriminative":[64],"criterion":[65],"order":[67],"enhance":[69],"output":[70],"SNRs.":[71],"A":[72],"Recurrent":[74],"Neural":[75],"Network":[76],"(RNN)":[77],"is":[78,100,144],"first":[79,173],"trained":[80,113],"small":[83],"subset":[84],"(roughly":[85],"one-fifth)":[86],"data":[89],"speech":[93,98],"specific":[94],"mask.":[95],"The":[96],"denoised":[97,115,180],"signal":[99],"then":[101],"directly":[102],"fed":[103],"input":[105],"convolutional":[109],"(CNN)":[112],"speech.":[116,181],"evaluate":[118],"standalone":[120],"performance":[121],"denoiser":[123],"terms":[125],"various":[127],"signal-to-noise":[128],"measures":[129],"discuss":[131],"its":[132],"contribution":[133],"towards":[134],"robust":[135],"AGR.":[136],"An":[137],"absolute":[138],"improvement":[139],"11.06%":[141],"13.33%":[143],"achieved":[145],"by":[146,171],"combined":[148],"pipeline":[149],"over":[150],"i-vector":[152],"SVM":[153],"baseline":[154],"0":[157],"dB":[158,161],"-5":[160],"SNR":[162],"conditions,":[163],"respectively.":[164],"further":[166],"analyse":[167],"information":[169],"captured":[170],"CNN":[174],"layer":[175],"both":[177],"noisy":[178]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}