{"id":"https://openalex.org/W2972984069","doi":"https://doi.org/10.21437/interspeech.2019-2652","title":"Unsupervised Raw Waveform Representation Learning for ASR","display_name":"Unsupervised Raw Waveform Representation Learning for ASR","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972984069","doi":"https://doi.org/10.21437/interspeech.2019-2652","mag":"2972984069"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2652","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mpra.ub.uni-muenchen.de/78247/1/MPRA_paper_78247.PDF","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Purvi Agrawal","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0122,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.829848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3451","last_page":"3455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.984000027179718,"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":0.7536450028419495},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7438069581985474},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6114274859428406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5343025922775269},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45793935656547546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4491901695728302},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4102017283439636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3747102618217468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33213144540786743},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1098828911781311}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536450028419495},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7438069581985474},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6114274859428406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343025922775269},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45793935656547546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4491901695728302},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4102017283439636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3747102618217468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33213144540786743},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1098828911781311},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2652","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai::78247","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/78247/1/MPRA_paper_78247.PDF","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai::78247","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/78247/1/MPRA_paper_78247.PDF","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2972984069.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1992475611","https://openalex.org/W2114719288","https://openalex.org/W2132037657","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2289394825","https://openalex.org/W2394873997","https://openalex.org/W2398826216","https://openalex.org/W2400622930","https://openalex.org/W2658929981","https://openalex.org/W2963175699"],"related_works":["https://openalex.org/W1974895211","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":{"In":[0,133],"this":[1,65,77],"paper,":[2],"we":[3],"propose":[4],"a":[5,69,112],"deep":[6,26],"representation":[7],"learning":[8,18],"approach":[9],"using":[10,43,68,98],"the":[11,24,32,61,84,89,93,99,105,136,140,150,184],"raw":[12],"speech":[13,113],"waveform":[14],"in":[15,111,146,165],"an":[16],"unsupervised":[17],"paradigm.":[19],"The":[20,38,51,74],"first":[21,62],"layer":[22,34,63,79,109],"of":[23,60,161],"proposed":[25,141],"model":[27,90],"performs":[28,35],"acoustic":[29,39],"filtering":[30,53,80,94],"while":[31],"subsequent":[33],"modulation":[36,52],"filtering.":[37],"filterbank":[40,152],"is":[41,54,66],"implemented":[42],"cosine-modulated":[44],"Gaussian":[45],"filters":[46],"whose":[47],"parameters":[48,91],"are":[49,81,96,117],"learned.":[50],"performed":[55],"on":[56,119,172,178,187],"log":[57],"transformed":[58],"outputs":[59,75],"and":[64,126,154,163,174,181],"achieved":[67],"skip":[70],"connection":[71],"based":[72],"architecture.":[73],"from":[76,139],"two":[78],"fed":[82],"to":[83],"variational":[85],"autoencoder":[86],"model.":[87],"All":[88],"including":[92],"layers":[95],"learned":[97,106,137],"VAE":[100],"cost":[101],"function.":[102],"We":[103],"employ":[104],"representations":[107,138],"(second":[108],"outputs)":[110],"recognition":[114],"task.":[115],"Experiments":[116],"conducted":[118],"Aurora-4":[120,179],"(additive":[121,128],"noise":[122,129],"with":[123,130],"channel":[124],"artifact)":[125],"CHiME-3":[127,188],"reverberation)":[131],"databases.":[132],"these":[134],"experiments,":[135],"framework":[142],"provide":[143],"significant":[144],"improvements":[145,160],"ASR":[147],"results":[148],"over":[149,169,183],"baseline":[151,170,185],"features":[153,171,186],"other":[155],"robust":[156],"front-ends":[157],"(average":[158],"relative":[159],"16":[162],"6":[164],"word":[166],"error":[167],"rate":[168],"clean":[173],"multi-condition":[175],"training,":[176],"respectively":[177],"dataset,":[180],"21":[182],"database).":[189],"Copyright":[190],"\u00c2\u00a9":[191],"2019":[192],"ISCA":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}