{"id":"https://openalex.org/W3197853473","doi":"https://doi.org/10.21437/interspeech.2021-1516","title":"Insights on Neural Representations for End-to-End Speech Recognition","display_name":"Insights on Neural Representations for End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197853473","doi":"https://doi.org/10.21437/interspeech.2021-1516","mag":"3197853473"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1516","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.09456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019525082","display_name":"Anna Ollerenshaw","orcid":"https://orcid.org/0000-0001-5779-1905"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anna Ollerenshaw","raw_affiliation_strings":["Speech and Hearing Research Group, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113981675","display_name":"Md Asif Jalal","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Md. Asif Jalal","raw_affiliation_strings":["Speech and Hearing Research Group, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Research Group, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019525082"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.8397,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78967835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4079","last_page":"4083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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/T10320","display_name":"Neural Networks and Applications","score":0.9805999994277954,"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/T11309","display_name":"Music and Audio Processing","score":0.9253000020980835,"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":0.7289559841156006},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6472170352935791},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.6325969696044922},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6007001996040344},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5252537131309509},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5172715783119202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5124650597572327},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5101943016052246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028614401817322},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4937652051448822},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4480781555175781},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42500966787338257},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4123244881629944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12398546934127808},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08003875613212585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289559841156006},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6472170352935791},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.6325969696044922},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6007001996040344},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5252537131309509},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5172715783119202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5124650597572327},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5101943016052246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028614401817322},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4937652051448822},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4480781555175781},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42500966787338257},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4123244881629944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12398546934127808},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08003875613212585},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2021-1516","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:187597","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:arXiv.org:2205.09456","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09456","pdf_url":"https://arxiv.org/pdf/2205.09456","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.09456","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09456","pdf_url":"https://arxiv.org/pdf/2205.09456","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1485103818","https://openalex.org/W1638081485","https://openalex.org/W2100235303","https://openalex.org/W2102113734","https://openalex.org/W2124338691","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2166637769","https://openalex.org/W2187242020","https://openalex.org/W2193413348","https://openalex.org/W2530876040","https://openalex.org/W2913292019","https://openalex.org/W2942810103","https://openalex.org/W2950976310","https://openalex.org/W2951603627","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963096987","https://openalex.org/W2963211739","https://openalex.org/W4246066915","https://openalex.org/W4287748764","https://openalex.org/W4294103325","https://openalex.org/W4297730150","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1565185441","https://openalex.org/W1968846550","https://openalex.org/W302711736","https://openalex.org/W2313359725","https://openalex.org/W3179968364","https://openalex.org/W2375550484","https://openalex.org/W3134705486","https://openalex.org/W2619932150","https://openalex.org/W2121524531","https://openalex.org/W2752621239"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,11,180,196],"recognition":[3,181,197],"(ASR)":[4],"models":[5],"aim":[6],"to":[7,19,37,45,127,192],"learn":[8],"a":[9,146],"generalised":[10],"representation.":[12],"However,":[13],"there":[14,144],"are":[15],"limited":[16,126],"tools":[17],"available":[18],"understand":[20,38],"the":[21,25,31,39,42,49,78,103,151,173],"internal":[22,79],"functions":[23],"and":[24,54,76,88,97],"effect":[26],"of":[27,58],"hierarchical":[28,115],"dependencies":[29,117],"within":[30,111],"model":[32],"architecture.":[33],"It":[34,105],"is":[35,124,137,145],"crucial":[36],"correlations":[40],"between":[41,51,81],"layer-wise":[43],"representations,":[44],"derive":[46],"insights":[47,171],"on":[48],"relationship":[50],"neural":[52,109,130,163,176],"representations":[53,110],"performance.":[55,182],"Previous":[56],"investigations":[57],"network":[59],"similarities":[60],"using":[61,92],"correlation":[62,94,116,161],"analysis":[63,95],"techniques":[64,186],"have":[65,178],"not":[66,138],"been":[67],"explored":[68],"for":[69,102],"End-to-End":[70],"ASR":[71],"models.":[72,198],"This":[73,135],"paper":[74],"analyses":[75],"explores":[77],"dynamics":[80],"layers":[82,113,157],"during":[83],"training":[84,152],"with":[85],"CNN,":[86],"LSTM":[87,141],"Transformer":[89,155],"based":[90],"approaches":[91],"Canonical":[93],"(CCA)":[96],"centered":[98],"kernel":[99],"alignment":[100],"(CKA)":[101],"experiments.":[104],"was":[106],"found":[107],"that":[108,175],"CNN":[112],"exhibit":[114,158],"as":[118,162,190],"layer":[119],"depth":[120,164],"increases":[121],"but":[122],"this":[123],"mostly":[125],"cases":[128],"where":[129],"representation":[131],"correlates":[132],"more":[133],"closely.":[134],"behaviour":[136],"observed":[139,149],"in":[140],"architecture,":[142],"however":[143],"bottom-up":[147],"pattern":[148],"across":[150],"process,":[153],"while":[154],"encoder":[156],"irregular":[159],"coefficiency":[160],"increases.":[165],"Altogether,":[166],"these":[167,185],"results":[168],"provide":[169],"new":[170],"into":[172],"role":[174],"architectures":[177],"upon":[179],"More":[183],"specifically,":[184],"can":[187],"be":[188],"used":[189],"indicators":[191],"build":[193],"better":[194],"performing":[195]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}