{"id":"https://openalex.org/W2705373224","doi":"https://doi.org/10.1109/icassp.2017.7953248","title":"Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features","display_name":"Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2705373224","doi":"https://doi.org/10.1109/icassp.2017.7953248","mag":"2705373224"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/3227e8cb-3b44-4854-8f40-54f78fc0ba9f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"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":"Ondrej Klejch","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"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":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5700","last_page":"5704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9983999729156494,"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":0.7794551849365234},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.7259553074836731},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6400737762451172},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6366604566574097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5558381080627441},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5431399345397949},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5334964394569397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511536717414856},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4395495355129242},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4226216971874237},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1433541476726532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794551849365234},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.7259553074836731},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6400737762451172},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6366604566574097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5558381080627441},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5431399345397949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5334964394569397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511536717414856},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4395495355129242},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4226216971874237},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1433541476726532},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2017.7953248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/3227e8cb-3b44-4854-8f40-54f78fc0ba9f","is_oa":true,"landing_page_url":"http://ieeexplore.ieee.org/document/7953248/","pdf_url":"http://hdl.handle.net/20.500.11820/3227e8cb-3b44-4854-8f40-54f78fc0ba9f","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/3227e8cb-3b44-4854-8f40-54f78fc0ba9f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3227e8cb-3b44-4854-8f40-54f78fc0ba9f","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Klejch, O, Bell, P & Renals, S 2017, Sequence-to-Sequence Models for Punctuated Transcription Combing Lexical and Acoustic Features. in The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017). Institute of Electrical and Electronics Engineers, pp. 5700-5704, 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, Louisiana, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7953248","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:zenodo.org:827244","is_oa":true,"landing_page_url":"https://zenodo.org/record/827244","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:pure.ed.ac.uk:publications/3227e8cb-3b44-4854-8f40-54f78fc0ba9f","is_oa":true,"landing_page_url":"http://ieeexplore.ieee.org/document/7953248/","pdf_url":"http://hdl.handle.net/20.500.11820/3227e8cb-3b44-4854-8f40-54f78fc0ba9f","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2705373224.pdf","grobid_xml":"https://content.openalex.org/works/W2705373224.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W61566120","https://openalex.org/W94670513","https://openalex.org/W171402391","https://openalex.org/W192736094","https://openalex.org/W222053410","https://openalex.org/W1451631119","https://openalex.org/W1504308419","https://openalex.org/W1524333225","https://openalex.org/W1526024327","https://openalex.org/W1587490638","https://openalex.org/W1847088711","https://openalex.org/W2095705004","https://openalex.org/W2103088716","https://openalex.org/W2113021982","https://openalex.org/W2113851376","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2166116787","https://openalex.org/W2169187092","https://openalex.org/W2220350356","https://openalex.org/W2247931231","https://openalex.org/W2250742840","https://openalex.org/W2288371874","https://openalex.org/W2294770573","https://openalex.org/W2395173459","https://openalex.org/W2398104528","https://openalex.org/W2403334028","https://openalex.org/W2406343628","https://openalex.org/W2407834842","https://openalex.org/W2408025694","https://openalex.org/W2513522215","https://openalex.org/W2962732637","https://openalex.org/W2962883855","https://openalex.org/W2963842982","https://openalex.org/W2963876447","https://openalex.org/W2964034111","https://openalex.org/W2964308564","https://openalex.org/W6600284362","https://openalex.org/W6603793917","https://openalex.org/W6607019473","https://openalex.org/W6607863627","https://openalex.org/W6608792757","https://openalex.org/W6628470722","https://openalex.org/W6631362777","https://openalex.org/W6635223454","https://openalex.org/W6638824847","https://openalex.org/W6674330103","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6684662674","https://openalex.org/W6685145238","https://openalex.org/W6688806467","https://openalex.org/W6712411474","https://openalex.org/W6713490458","https://openalex.org/W6713560684","https://openalex.org/W6714054690"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W3163320880","https://openalex.org/W2365703075"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,49],"present":[4],"an":[5],"extension":[6,20],"of":[7,67,76,87],"our":[8],"previously":[9],"described":[10],"neural":[11,94],"machine":[12,95],"translation":[13,96],"based":[14,97],"system":[15,23,53],"for":[16],"punctuated":[17],"transcription.":[18],"This":[19],"allows":[21],"the":[22,37,41,91],"to":[24,31],"map":[25],"from":[26],"per":[27],"frame":[28],"acoustic":[29,57,79],"features":[30,58,68,80],"word":[32],"level":[33],"representations":[34],"by":[35],"replacing":[36],"traditional":[38],"encoder":[39],"in":[40,85],"encoder-decoder":[42],"architecture":[43],"with":[44],"a":[45,52,64,82],"hierarchical":[46],"encoder.":[47],"Furthermore,":[48],"show":[50],"that":[51],"combining":[54],"lexical":[55,77,93],"and":[56,78],"significantly":[59],"outperforms":[60],"systems":[61],"using":[62],"only":[63],"single":[65],"source":[66],"on":[69],"all":[70],"measured":[71],"punctuation":[72],"marks.":[73],"The":[74],"combination":[75],"achieves":[81],"significant":[83],"improvement":[84],"F-Measure":[86],"1.5":[88],"absolute":[89],"over":[90],"purely":[92],"system.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}