{"id":"https://openalex.org/W2944130999","doi":"https://doi.org/10.1109/iscslp.2018.8706697","title":"Enhanced Denoising Auto-Encoder for Robust Speech Recognition in Unseen Noise Conditions","display_name":"Enhanced Denoising Auto-Encoder for Robust Speech Recognition in Unseen Noise Conditions","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944130999","doi":"https://doi.org/10.1109/iscslp.2018.8706697","mag":"2944130999"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5052564654","display_name":"Sonal Joshi","orcid":"https://orcid.org/0000-0001-8020-7551"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sonal Joshi","raw_affiliation_strings":["TCS Innovation Lab-Mumbai, Yantra Park, Thane, Maharashtra, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Innovation Lab-Mumbai, Yantra Park, Thane, Maharashtra, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103959037","display_name":"Ashish Panda","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Panda","raw_affiliation_strings":["TCS Innovation Lab-Mumbai, Yantra Park, Thane, Maharashtra, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Innovation Lab-Mumbai, Yantra Park, Thane, Maharashtra, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077025751","display_name":"Biswajit Das","orcid":"https://orcid.org/0000-0002-0817-2929"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Biswajit Das","raw_affiliation_strings":["TCS Innovation Lab-Mumbai, Yantra Park, Thane, Maharashtra, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Innovation Lab-Mumbai, Yantra Park, Thane, Maharashtra, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1663,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51332855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"47","issue":null,"first_page":"359","last_page":"363"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428072690963745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7230322360992432},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6449596285820007},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6191549301147461},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.6100605726242065},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6023789048194885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.517760694026947},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5114211440086365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4673968255519867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428072690963745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7230322360992432},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6449596285820007},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6191549301147461},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.6100605726242065},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6023789048194885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517760694026947},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5114211440086365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4673968255519867},{"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/iscslp.2018.8706697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1553437616","https://openalex.org/W1601124178","https://openalex.org/W1635512741","https://openalex.org/W1974387177","https://openalex.org/W2051428568","https://openalex.org/W2116746197","https://openalex.org/W2117671523","https://openalex.org/W2125234026","https://openalex.org/W2128653836","https://openalex.org/W2137401359","https://openalex.org/W2149535104","https://openalex.org/W2173629880","https://openalex.org/W2290318471","https://openalex.org/W2396756519","https://openalex.org/W2402146185","https://openalex.org/W2515753980","https://openalex.org/W2584408992","https://openalex.org/W2604496056","https://openalex.org/W2630683241","https://openalex.org/W2671186495","https://openalex.org/W2680548194","https://openalex.org/W2750418488","https://openalex.org/W2753723464","https://openalex.org/W2766177643","https://openalex.org/W2963488660","https://openalex.org/W4294576147","https://openalex.org/W6631362777","https://openalex.org/W6677592687","https://openalex.org/W6680646222","https://openalex.org/W6696830301","https://openalex.org/W6712567857","https://openalex.org/W6712930963","https://openalex.org/W6744546696"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W2373767407","https://openalex.org/W3168109306","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W3034789145","https://openalex.org/W4367628250","https://openalex.org/W197907117"],"abstract_inverted_index":{"We":[0,38,154],"present":[1],"a":[2,23,54],"robust":[3],"front-end":[4],"processing":[5],"method":[6],"for":[7],"speech":[8,51],"recognition":[9,52],"in":[10,32,45,57,67,79,90,168],"unseen":[11,35,80,169],"noise":[12,36,59,81,124,170],"conditions.":[13,37],"Towards":[14],"this":[15,132],"end,":[16],"we":[17,99,134],"have":[18],"investigated":[19],"the":[20,42,47,50,68,71,77,91,94,103,107,115,122,128,136,162,165,174,179],"efficacy":[21,163],"of":[22,49,70,93,138,164],"Time":[24],"Delay":[25],"Neural":[26],"Network":[27],"based":[28],"Denoising":[29],"Auto-Encoder":[30],"(TDNN-DAE)":[31],"seen":[33,58],"and":[34,150,172],"show":[39,155],"that":[40,156,173],"while":[41],"TDNN-DAE":[43,108,116,166,177],"succeeds":[44],"improving":[46],"performance":[48,78,137],"by":[53,127],"large":[55],"margin":[56],"conditions":[60,82,171],"(noise":[61,83],"encountered":[62,84],"during":[63,85],"decoding":[64,86],"was":[65,87],"used":[66,89],"training":[69,92,104],"TDNN-DAE),":[72],"it":[73],"fails":[74],"to":[75,101,106,120],"improve":[76,161],"not":[88],"TDNN-DAE).":[95],"To":[96],"address":[97,121],"this,":[98],"propose":[100],"pre-process":[102],"input":[105],"using":[109],"an":[110],"enhancement":[111,129,140,159],"technique.":[112,130],"In":[113],"essence,":[114],"is":[117],"being":[118],"trained":[119],"residual":[123],"left":[125],"behind":[126],"For":[131],"task,":[133],"compare":[135],"two":[139],"techniques,":[141],"namely":[142],"Vector":[143],"Taylor":[144],"Series":[145],"with":[146],"Acoustic":[147],"Masking":[148],"(VTS-AM)":[149],"Spectral":[151],"Subtraction":[152],"(SS).":[153],"both":[157],"these":[158],"techniques":[160],"significantly":[167],"VTS-AM":[175],"enhanced":[176,181],"outperforms":[178],"SS":[180],"TDNN-DAE.":[182]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
