{"id":"https://openalex.org/W2745441477","doi":"https://doi.org/10.21437/interspeech.2017-901","title":"Speech Representation Learning Using Unsupervised Data-Driven Modulation Filtering for Robust ASR","display_name":"Speech Representation Learning Using Unsupervised Data-Driven Modulation Filtering for Robust ASR","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2745441477","doi":"https://doi.org/10.21437/interspeech.2017-901","mag":"2745441477"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-901","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5050546237","display_name":"Purvi Agrawal","orcid":"https://orcid.org/0000-0002-1165-8348"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Purvi Agrawal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050546237"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5593,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65474974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2446","last_page":"2450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9959999918937683,"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":0.7929472327232361},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6704243421554565},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5554085969924927},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5399347543716431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4777735471725464},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4609798192977905},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.43697795271873474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3975018858909607},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08312025666236877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929472327232361},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6704243421554565},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5554085969924927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5399347543716431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4777735471725464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4609798192977905},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.43697795271873474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3975018858909607},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08312025666236877},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2017-901","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai::74709","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W182885046","https://openalex.org/W1510881793","https://openalex.org/W1524333225","https://openalex.org/W1627087495","https://openalex.org/W2023262923","https://openalex.org/W2099866409","https://openalex.org/W2100495367","https://openalex.org/W2113427327","https://openalex.org/W2114719288","https://openalex.org/W2116064496","https://openalex.org/W2130325614","https://openalex.org/W2130426352","https://openalex.org/W2132606418","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2159373586","https://openalex.org/W2161224286","https://openalex.org/W2165720259","https://openalex.org/W2167763959","https://openalex.org/W2242685705","https://openalex.org/W2394873997","https://openalex.org/W2963175699"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W3174759195","https://openalex.org/W3167013339","https://openalex.org/W4287121366","https://openalex.org/W60493759","https://openalex.org/W4308619659","https://openalex.org/W3213069564","https://openalex.org/W4378421684","https://openalex.org/W4294203825","https://openalex.org/W1505616161"],"abstract_inverted_index":{"The":[0,118],"performance":[1],"of":[2,22,45,105,166,191],"an":[3,89],"automatic":[4],"speech":[5,53,62,95,181,200],"recognition":[6],"(ASR)":[7],"system":[8],"degrades":[9],"severely":[10],"in":[11,16,24,29,50,88,171],"noisy":[12],"and":[13,131,154],"reverberant":[14,180],"environments":[15],"part":[17],"due":[18],"to":[19,112,152,158],"the":[20,25,30,34,37,43,81,93,114,139,144,175,184,189,192],"lack":[21],"robustness":[23,151],"underlying":[26],"representations":[27,49,77,115],"used":[28],"ASR":[31,140,176],"system.":[32],"On":[33],"other":[35,159],"hand,":[36],"auditory":[38],"processing":[39],"studies":[40],"have":[41],"shown":[42],"importance":[44],"modulation":[46,71,146],"filtered":[47],"spectrogram":[48],"robust":[51],"human":[52],"recognition.":[54,201],"Inspired":[55],"by":[56],"these":[57,137],"evidences,":[58],"we":[59],"propose":[60],"a":[61],"representation":[63,194],"learning":[64,195],"paradigm":[65],"using":[66,80],"data-driven":[67],"2-":[68],"D":[69],"spectro-temporal":[70],"filter":[72,98],"learning.":[73],"In":[74,136],"particular,":[75],"multiple":[76],"are":[78,120],"derived":[79],"convolutional":[82],"restricted":[83],"Boltzmann":[84],"machine":[85],"(CRBM)":[86],"model":[87],"unsupervised":[90],"manner":[91],"from":[92,143,183],"input":[94],"spectrogram.":[96],"A":[97],"selection":[99],"criteria":[100],"based":[101],"on":[102,122,179],"average":[103],"number":[104],"active":[106],"hidden":[107],"units":[108],"is":[109],"also":[110],"employed":[111],"select":[113],"for":[116,197],"ASR.":[117],"experiments":[119,177],"performed":[121,178],"Wall":[123],"Street":[124],"Journal":[125],"(WSJ)":[126],"Aurora-4":[127],"database":[128],"with":[129],"clean":[130,172],"multi":[132],"condition":[133],"training":[134],"setup.":[135],"experiments,":[138],"results":[141],"obtained":[142],"proposed":[145,193],"filtering":[147],"approach":[148],"shows":[149],"significant":[150],"noise":[153],"channel":[155],"distortions":[156],"compared":[157],"feature":[160],"extraction":[161],"methods":[162],"(average":[163],"relative":[164],"improvements":[165],"19":[167],"over":[168],"baseline":[169],"features":[170],"training).":[173],"Furthermore,":[174],"data":[182],"REVERB":[185],"challenge":[186],"corpus":[187],"highlight":[188],"benefits":[190],"scheme":[196],"far":[198],"field":[199]},"counts_by_year":[{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}