{"id":"https://openalex.org/W2888991776","doi":"https://doi.org/10.21437/interspeech.2018-2420","title":"Wide Learning for Auditory Comprehension","display_name":"Wide Learning for Auditory Comprehension","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888991776","doi":"https://doi.org/10.21437/interspeech.2018-2420","mag":"2888991776"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2420","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/2583674","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002918682","display_name":"Elnaz Shafaei-Bajestan","orcid":"https://orcid.org/0000-0002-1441-5608"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Elnaz Shafaei-Bajestan","raw_affiliation_strings":["Quantitative Linguistics, Eberhard Karls Universit\u00e4t T\u00fcbingen, T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Quantitative Linguistics, Eberhard Karls Universit\u00e4t T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087366961","display_name":"R. Harald Baayen","orcid":"https://orcid.org/0000-0003-3178-3944"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"R. Harald Baayen","raw_affiliation_strings":["Quantitative Linguistics, Eberhard Karls Universit\u00e4t T\u00fcbingen, T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Quantitative Linguistics, Eberhard Karls Universit\u00e4t T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002918682"],"corresponding_institution_ids":["https://openalex.org/I8087733"],"apc_list":null,"apc_paid":null,"fwci":3.3186,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93389023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9779000282287598,"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/T11309","display_name":"Music and Audio Processing","score":0.9779000282287598,"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/T10860","display_name":"Speech and Audio Processing","score":0.9757000207901001,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6747729778289795},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5014302730560303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35532256960868835},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0969264805316925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747729778289795},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5014302730560303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35532256960868835},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0969264805316925}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-2420","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:2583674","is_oa":true,"landing_page_url":"https://zenodo.org/record/2583674","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:2583674","is_oa":true,"landing_page_url":"https://zenodo.org/record/2583674","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W160989634","https://openalex.org/W1487022053","https://openalex.org/W1523422326","https://openalex.org/W1757417856","https://openalex.org/W1777013583","https://openalex.org/W1922655562","https://openalex.org/W1965349238","https://openalex.org/W1989462718","https://openalex.org/W2037784950","https://openalex.org/W2042354347","https://openalex.org/W2043983639","https://openalex.org/W2055900849","https://openalex.org/W2067965259","https://openalex.org/W2114330138","https://openalex.org/W2133590932","https://openalex.org/W2592432091","https://openalex.org/W2606425707","https://openalex.org/W2742808001","https://openalex.org/W2753261897","https://openalex.org/W2896260449","https://openalex.org/W3187397227","https://openalex.org/W3216401400","https://openalex.org/W4311798714","https://openalex.org/W4399550896"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Classical":[0],"linguistic,":[1],"cognitive":[2,49],"and":[3,9,17,25,91,136],"engineering":[4],"models":[5],"for":[6,15],"speech":[7,31,154],"recognition":[8,32,179],"human":[10],"auditory":[11,52],"comprehension":[12,53,192],"posit":[13],"representations":[14],"sounds":[16],"words":[18],"that":[19,38,61,84],"mediate":[20],"between":[21,128],"the":[22,100,116,129,191],"acoustic":[23,130],"signal":[24],"interpretation.":[26],"Recent":[27],"advances":[28],"in":[29,155],"automatic":[30],"have":[33],"shown,":[34],"using":[35],"deep":[36,59,75],"learning,":[37],"state-of-the-art":[39],"performance":[40,146],"is":[41,80,118,181],"obtained":[42],"without":[43],"such":[44],"units.":[45],"We":[46],"present":[47,177],"a":[48,119,168,172,187],"model":[50,79,117],"of":[51,69,89,103,115,186,193],"based":[54],"on":[55,64,99,153,159],"wide":[56,122,174],"rather":[57,157],"than":[58,158],"learning":[60],"was":[62,163],"trained":[63,152],"20":[65],"to":[66,140,171,183],"80":[67],"hours":[68],"TV":[70],"news":[71],"broadcasts.":[72],"Just":[73],"as":[74,134,143],"network":[76,124,170],"models,":[77],"our":[78],"an":[81],"end-to-end":[82],"system":[83,189],"does":[85],"not":[86],"make":[87],"use":[88],"phonemes":[90],"phonological":[92],"wordform":[93],"representations.":[94],"Nevertheless,":[95],"it":[96],"performs":[97],"well":[98],"difficult":[101],"task":[102],"single":[104],"word":[105,178],"identification":[106],"(model":[107],"accuracy":[108],"11.37%,":[109],"Mozilla":[110],"DeepSpeech:":[111],"4.45%).":[112],"The":[113,176],"architecture":[114],"simple":[120],"two-layered":[121],"neural":[123],"with":[125],"weighted":[126],"connections":[127],"frequency":[131],"band":[132],"features":[133],"inputs":[135],"lexical":[137],"outcomes":[138],"(pointers":[139],"semantic":[141],"vectors)":[142],"outputs.":[144],"Model":[145],"shows":[147],"hardly":[148],"any":[149],"degredation":[150],"when":[151],"noise":[156],"clean":[160],"speech.":[161,195],"Performance":[162],"further":[164],"enhanced":[165],"by":[166],"adding":[167],"second":[169],"standard":[173],"network.":[175],"module":[180],"designed":[182],"become":[184],"part":[185],"larger":[188],"modeling":[190],"running":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}