{"id":"https://openalex.org/W2963795358","doi":"https://doi.org/10.21437/interspeech.2016-40","title":"Segmental Recurrent Neural Networks for End-to-End Speech Recognition","display_name":"Segmental Recurrent Neural Networks for End-to-End Speech Recognition","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2963795358","doi":"https://doi.org/10.21437/interspeech.2016-40","mag":"2963795358"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/20.500.11820/78ad24a9-2f17-4c0e-8906-d29fa92364bb","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014554970","display_name":"Lingpeng Kong","orcid":"https://orcid.org/0000-0002-9033-2724"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingpeng Kong","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111222692","display_name":"Chris Dyer","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Dyer","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088517824","display_name":"Noah A. Smith","orcid":"https://orcid.org/0000-0002-2310-6380"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah A. Smith","raw_affiliation_strings":["Computer Science & Engineering, The University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, The University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8779687881469727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7286438345909119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6758383512496948},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5249329209327698},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4956241846084595},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.43855834007263184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3758606016635895}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8779687881469727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286438345909119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6758383512496948},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5249329209327698},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4956241846084595},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.43855834007263184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3758606016635895}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2016-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/78ad24a9-2f17-4c0e-8906-d29fa92364bb","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/78ad24a9-2f17-4c0e-8906-d29fa92364bb","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Kong, L, Dyer, C, Smith, N A & Renals, S 2016, Segmental Recurrent Neural Networks for End-to-end Speech Recognition. in Proceedings of Interspeech 2016. Interspeech, San Francisco, United States, pp. 385-389, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-40","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/78ad24a9-2f17-4c0e-8906-d29fa92364bb","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/78ad24a9-2f17-4c0e-8906-d29fa92364bb","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Kong, L, Dyer, C, Smith, N A & Renals, S 2016, Segmental Recurrent Neural Networks for End-to-end Speech Recognition. in Proceedings of Interspeech 2016. Interspeech, San Francisco, United States, pp. 385-389, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-40","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/78ad24a9-2f17-4c0e-8906-d29fa92364bb","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/78ad24a9-2f17-4c0e-8906-d29fa92364bb","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Kong, L, Dyer, C, Smith, N A & Renals, S 2016, Segmental Recurrent Neural Networks for End-to-end Speech Recognition. in Proceedings of Interspeech 2016. Interspeech, San Francisco, United States, pp. 385-389, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-40","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W973008471","https://openalex.org/W1524333225","https://openalex.org/W1591801644","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W1942035323","https://openalex.org/W1978741356","https://openalex.org/W2064675550","https://openalex.org/W2083393647","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2103945478","https://openalex.org/W2111535841","https://openalex.org/W2131700150","https://openalex.org/W2140409019","https://openalex.org/W2143612262","https://openalex.org/W2147880316","https://openalex.org/W2151660570","https://openalex.org/W2156615793","https://openalex.org/W2158188757","https://openalex.org/W2395342389","https://openalex.org/W2406482790","https://openalex.org/W2962875366","https://openalex.org/W2963688273","https://openalex.org/W2963920996","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2578422401","https://openalex.org/W1584270863","https://openalex.org/W1595652908","https://openalex.org/W2603525251","https://openalex.org/W4285294654","https://openalex.org/W2085961337","https://openalex.org/W2950022897","https://openalex.org/W2890297197","https://openalex.org/W2386241395","https://openalex.org/W2357447513"],"abstract_inverted_index":{"We":[0,110,117],"study":[1],"the":[2,14,57,65,70,97,102,105,114,125,129,136],"segmental":[3,15,71],"recurrent":[4,22],"neural":[5,23],"network":[6,24],"for":[7,27],"end-to-end":[8],"acoustic":[9,35],"modelling.":[10],"This":[11],"model":[12,53,76],"connects":[13],"conditional":[16],"random":[17],"field":[18],"(CRF)":[19],"with":[20,69],"a":[21,142],"(RNN)":[25],"used":[26,141],"feature":[28],"extraction.":[29],"Compared":[30],"to":[31,45,99],"most":[32],"previous":[33],"CRF-based":[34],"models,":[36],"it":[37],"does":[38],"not":[39],"rely":[40],"on":[41,113],"an":[42],"external":[43],"system":[44],"provide":[46],"features":[47,61],"or":[48],"segmentation":[49],"boundaries.":[50],"Instead,":[51],"this":[52,75,85],"marginalises":[54],"out":[55],"all":[56],"possible":[58],"segmentations,":[59],"and":[60,79,91,145],"are":[62],"extracted":[63],"from":[64,124],"RNN":[66],"trained":[67,82],"together":[68],"CRF.":[72],"In":[73,84],"essence,":[74],"is":[77],"self-contained":[78],"can":[80],"be":[81],"end-to-end.":[83],"paper,":[86],"we":[87,139],"discuss":[88],"practical":[89],"training":[90,103],"decoding":[92,127],"issues":[93],"as":[94,96],"well":[95],"method":[98],"speed":[100],"up":[101],"in":[104],"context":[106],"of":[107],"speech":[108],"recognition.":[109],"performed":[111],"experiments":[112],"TIMIT":[115],"dataset.":[116],"achieved":[118],"17.3":[119],"phone":[120],"error":[121],"rate":[122],"(PER)":[123],"first-pass":[126],"---":[128],"best":[130],"reported":[131],"result":[132],"using":[133,147],"CRFs,":[134],"despite":[135],"fact":[137],"that":[138],"only":[140],"zeroth-order":[143],"CRF":[144],"without":[146],"any":[148],"language":[149],"model.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}