{"id":"https://openalex.org/W2022011789","doi":"https://doi.org/10.1109/tasl.2011.2116010","title":"Deep and Wide: Multiple Layers in Automatic Speech Recognition","display_name":"Deep and Wide: Multiple Layers in Automatic Speech Recognition","publication_year":2011,"publication_date":"2011-02-18","ids":{"openalex":"https://openalex.org/W2022011789","doi":"https://doi.org/10.1109/tasl.2011.2116010","mag":"2022011789"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2116010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2116010","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112003894"],"corresponding_institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":15.9609,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.9909168,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"20","issue":"1","first_page":"7","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.8251892328262329},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7007504105567932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6422744989395142},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6287180185317993},{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.5839653611183167},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5171558260917664},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.49895620346069336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49452778697013855},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4667750895023346},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.4110279977321625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40260380506515503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3557084798812866},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10572850704193115},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08220377564430237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251892328262329},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7007504105567932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6422744989395142},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6287180185317993},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.5839653611183167},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5171558260917664},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.49895620346069336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49452778697013855},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4667750895023346},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.4110279977321625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40260380506515503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3557084798812866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10572850704193115},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08220377564430237},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2011.2116010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2116010","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W16789520","https://openalex.org/W96431220","https://openalex.org/W190289757","https://openalex.org/W1495547083","https://openalex.org/W1518070176","https://openalex.org/W1553004968","https://openalex.org/W1608451537","https://openalex.org/W1749792876","https://openalex.org/W1995752403","https://openalex.org/W2012352874","https://openalex.org/W2021396747","https://openalex.org/W2052406154","https://openalex.org/W2059988466","https://openalex.org/W2063223471","https://openalex.org/W2071489795","https://openalex.org/W2084514013","https://openalex.org/W2097560587","https://openalex.org/W2102775757","https://openalex.org/W2103359087","https://openalex.org/W2125610823","https://openalex.org/W2130361043","https://openalex.org/W2134900903","https://openalex.org/W2141499240","https://openalex.org/W2151484683","https://openalex.org/W2165712214","https://openalex.org/W2256289078","https://openalex.org/W4255982026"],"related_works":["https://openalex.org/W2055105357","https://openalex.org/W2153819599","https://openalex.org/W2255426644","https://openalex.org/W2072124641","https://openalex.org/W2167093538","https://openalex.org/W2018956713","https://openalex.org/W2081479354","https://openalex.org/W2113107605","https://openalex.org/W3204693335","https://openalex.org/W1971573522"],"abstract_inverted_index":{"This":[0,64],"paper":[1,65],"reviews":[2],"a":[3],"line":[4],"of":[5,29,32,41,50,53,81],"research":[6],"carried":[7],"out":[8],"over":[9],"the":[10,27,35,48,70,84],"last":[11],"decade":[12],"in":[13],"speech":[14],"recognition":[15],"assisted":[16],"by":[17],"discriminatively":[18],"trained,":[19],"feedforward":[20],"networks.":[21],"The":[22],"particular":[23],"focus":[24],"is":[25,45],"on":[26,47],"use":[28,49],"multiple":[30,51],"layers":[31],"processing":[33,72],"preceding":[34],"hidden":[36],"Markov":[37],"model":[38],"based":[39],"decoding":[40],"word":[42],"sequences.":[43],"Emphasis":[44],"placed":[46],"streams":[52],"highly":[54],"dimensioned":[55],"layers,":[56],"which":[57,87],"have":[58],"proven":[59],"useful":[60],"for":[61,77],"this":[62,78],"purpose.":[63],"ultimately":[66],"concludes":[67],"that":[68],"while":[69],"deep":[71],"structures":[73],"can":[74,94],"provide":[75],"improvements":[76],"genre,":[79],"choice":[80],"features":[82],"and":[83],"structure":[85],"with":[86],"they":[88],"are":[89],"incorporated,":[90],"including":[91],"layer":[92],"width,":[93],"also":[95],"be":[96],"significant":[97],"factors.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}