{"id":"https://openalex.org/W2907522012","doi":"https://doi.org/10.1109/icapr.2017.8593069","title":"Sub-band Autoencoder features for Automatic Speech Recognition","display_name":"Sub-band Autoencoder features for Automatic Speech Recognition","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2907522012","doi":"https://doi.org/10.1109/icapr.2017.8593069","mag":"2907522012"},"language":"en","primary_location":{"id":"doi:10.1109/icapr.2017.8593069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2017.8593069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003062385","display_name":"Meet Soni","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Meet H. Soni","raw_affiliation_strings":["DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104071101","display_name":"Manisha Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manisha Sharma","raw_affiliation_strings":["DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22919087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"521","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.9987999796867371,"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/autoencoder","display_name":"Autoencoder","score":0.8963949680328369},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.8390378952026367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7487666010856628},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7469342350959778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7327399253845215},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.722874641418457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5790234208106995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5205296277999878},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5019955635070801},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4987611770629883},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4746333360671997},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43639615178108215},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4100600779056549},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.29009175300598145},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.20008349418640137},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10818707942962646}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8963949680328369},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8390378952026367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487666010856628},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7469342350959778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7327399253845215},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.722874641418457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5790234208106995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5205296277999878},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5019955635070801},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4987611770629883},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4746333360671997},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43639615178108215},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4100600779056549},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.29009175300598145},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.20008349418640137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10818707942962646},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icapr.2017.8593069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2017.8593069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1507423462","https://openalex.org/W1538131130","https://openalex.org/W1970088388","https://openalex.org/W1973681148","https://openalex.org/W1982109178","https://openalex.org/W1993721840","https://openalex.org/W2026369565","https://openalex.org/W2100495367","https://openalex.org/W2103359087","https://openalex.org/W2105099419","https://openalex.org/W2123237149","https://openalex.org/W2163922914","https://openalex.org/W2168013545","https://openalex.org/W2168249605","https://openalex.org/W2290318471","https://openalex.org/W2296581541","https://openalex.org/W2395849284","https://openalex.org/W2396030159","https://openalex.org/W2398826216","https://openalex.org/W2401869809","https://openalex.org/W2405774341","https://openalex.org/W2407127962","https://openalex.org/W2407828524","https://openalex.org/W2919115771","https://openalex.org/W6632100814","https://openalex.org/W6675321185","https://openalex.org/W6678292227","https://openalex.org/W6697251715","https://openalex.org/W6712466924","https://openalex.org/W6712560600","https://openalex.org/W6713197546","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W1980604799","https://openalex.org/W2043000765","https://openalex.org/W2907522012","https://openalex.org/W2114026179","https://openalex.org/W2108641942","https://openalex.org/W2015876361","https://openalex.org/W2131486661","https://openalex.org/W3086174161","https://openalex.org/W2562286514","https://openalex.org/W1959176866"],"abstract_inverted_index":{"Recently,":[0],"unsupervised":[1],"representation":[2,35],"learning":[3],"to":[4,45,74,117],"learn":[5],"the":[6],"features":[7,52,58,131],"from":[8,40],"speech":[9,17,48,75,137],"signals":[10],"has":[11],"seen":[12],"a":[13,25],"tremendous":[14],"upsurge":[15],"for":[16,34,47],"processing":[18],"applications.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,86,105],"investigate":[24],"modified":[26],"architecture":[27],"of":[28,96,109,126],"autoencoder":[29,32],"namely,":[30],"subband":[31],"(SBAE)":[33],"learning.":[36],"Features":[37],"were":[38,59],"learned":[39],"spectrogram":[41],"as":[42,56],"an":[43,88],"input":[44],"SBAE":[46,51,130],"recognition":[49,76],"task.":[50],"and":[53,64,80,129],"Mel-filterbank":[54,99,127],"energies":[55,100,128],"spectral":[57],"trained":[60,122],"separately":[61],"on":[62,78,93,113,123],"DNN":[63,121],"then":[65],"system":[66,124],"combination":[67,125],"is":[68],"used.":[69],"This":[70],"technique":[71],"was":[72],"applied":[73],"task":[77],"TIMIT":[79,84],"WSJO":[81,103],"databases.":[82],"On":[83],"database,":[85,104],"achieved":[87,106],"absolute":[89],"improvement":[90,108],"in":[91,111,136],"PER":[92],"test":[94,114],"set":[95],"3%":[97],"over":[98],"alone.":[101],"For":[102],"relative":[107],"9.89%":[110],"WER":[112],"sets":[115],"compared":[116],"filterbank":[118],"energies.":[119],"Hence,":[120],"provide":[132],"complementary":[133],"information":[134],"present":[135],"signal.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}