{"id":"https://openalex.org/W2786539019","doi":"https://doi.org/10.1109/asru.2017.8268981","title":"Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features","display_name":"Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786539019","doi":"https://doi.org/10.1109/asru.2017.8268981","mag":"2786539019"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268981","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/8e996f00-dd9e-4339-b88f-455597e82a0a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121096","display_name":"Dexerials (Japan)","ror":"https://ror.org/03p330m15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210121096"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Center for Speech Technology Research, University of Edinburgh, Edinburgh, UK","System R&D Group, R&D Platform Sony Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"System R&D Group, R&D Platform Sony Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210121096"]}]},{"author_position":"middle","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":["Center for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center 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":["Center for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center 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":["Center for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8414851427078247},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7871416211128235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6338992714881897},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6299231052398682},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5940419435501099},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5075656175613403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5032822489738464},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4803934693336487},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4736959934234619},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4660227298736572},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.46359625458717346},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.42024195194244385},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.41467154026031494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3388826251029968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414851427078247},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7871416211128235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6338992714881897},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6299231052398682},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5940419435501099},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5075656175613403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5032822489738464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4803934693336487},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4736959934234619},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4660227298736572},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.46359625458717346},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.42024195194244385},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41467154026031494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3388826251029968},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2017.8268981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268981","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/8e996f00-dd9e-4339-b88f-455597e82a0a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8e996f00-dd9e-4339-b88f-455597e82a0a","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":"Tsunoo, E, Klejch, O, Bell, P & Renals, S 2018, Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features. in 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 525-532, 2017 IEEE Automatic Speech Recognition and Understanding Workshop , Okinawa, Japan, 16/12/17. https://doi.org/10.1109/ASRU.2017.8268981","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/8e996f00-dd9e-4339-b88f-455597e82a0a","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/8268981/","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/8e996f00-dd9e-4339-b88f-455597e82a0a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8e996f00-dd9e-4339-b88f-455597e82a0a","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":"Tsunoo, E, Klejch, O, Bell, P & Renals, S 2018, Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features. in 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 525-532, 2017 IEEE Automatic Speech Recognition and Understanding Workshop , Okinawa, Japan, 16/12/17. https://doi.org/10.1109/ASRU.2017.8268981","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W113396932","https://openalex.org/W179875071","https://openalex.org/W941230081","https://openalex.org/W1540940911","https://openalex.org/W1576034263","https://openalex.org/W1586171079","https://openalex.org/W1607558779","https://openalex.org/W1626945812","https://openalex.org/W1815076433","https://openalex.org/W1828401780","https://openalex.org/W1837399425","https://openalex.org/W1880262756","https://openalex.org/W1994448786","https://openalex.org/W2018627475","https://openalex.org/W2091425152","https://openalex.org/W2100163972","https://openalex.org/W2107743791","https://openalex.org/W2107755572","https://openalex.org/W2126623305","https://openalex.org/W2131342762","https://openalex.org/W2143720614","https://openalex.org/W2153383412","https://openalex.org/W2157391896","https://openalex.org/W2158266063","https://openalex.org/W2167055684","https://openalex.org/W2172125983","https://openalex.org/W2251849926","https://openalex.org/W2259472270","https://openalex.org/W2288371874","https://openalex.org/W2397041827","https://openalex.org/W2402268235","https://openalex.org/W2426479676","https://openalex.org/W2509596028","https://openalex.org/W2509752738","https://openalex.org/W2586117383","https://openalex.org/W2746152375","https://openalex.org/W2998704965","https://openalex.org/W3028832680","https://openalex.org/W3122775348","https://openalex.org/W4233135949","https://openalex.org/W4285719527","https://openalex.org/W6634275767","https://openalex.org/W6635289007","https://openalex.org/W6636660855","https://openalex.org/W6638545294","https://openalex.org/W6638575021","https://openalex.org/W6639001170","https://openalex.org/W6639619044","https://openalex.org/W6680532216","https://openalex.org/W6683422417","https://openalex.org/W6685512947","https://openalex.org/W6692563993","https://openalex.org/W6712032945","https://openalex.org/W6732966863","https://openalex.org/W6778281501","https://openalex.org/W6789176730"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4288108708","https://openalex.org/W4387163678","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W3173606726","https://openalex.org/W2904359912"],"abstract_inverted_index":{"A":[0],"broadcast":[1],"news":[2,24],"stream":[3],"consists":[4],"of":[5,8,20,58,95,102,129],"a":[6,32,37,46,56,140],"number":[7],"stories":[9,21],"and":[10,45,60,69,89],"it":[11],"is":[12],"an":[13],"important":[14],"task":[15,92],"to":[16,75,114,144],"find":[17],"the":[18,28,73,79,86,122,130],"boundaries":[19],"automatically":[22],"in":[23],"analysis.":[25],"We":[26,82],"capture":[27],"topic":[29,52,87,125],"structure":[30],"using":[31],"hierarchical":[33,123],"model":[34,74],"based":[35],"on":[36,85],"Recurrent":[38],"Neural":[39],"Network":[40],"(RNN)":[41],"sentence":[42,80],"modeling":[43,53,126],"layer":[44],"bidirectional":[47],"Long":[48],"Short-Term":[49],"Memory":[50],"(LSTM)":[51],"layer,":[54],"with":[55,67,99,134,139],"fusion":[57,131],"acoustic":[59],"lexical":[61],"features.":[62],"Both":[63],"features":[64],"are":[65],"accumulated":[66],"RNNs":[68],"trained":[70,98],"jointly":[71],"within":[72],"be":[76],"fused":[77],"at":[78],"level.":[81],"conduct":[83],"experiments":[84],"detection":[88],"tracking":[90],"(TDT4)":[91],"comparing":[93],"combinations":[94],"two":[96],"modalities":[97],"limited":[100],"amount":[101],"parallel":[103],"data.":[104],"Further":[105],"we":[106],"utilize":[107],"additional":[108,135],"sufficient":[109],"text":[110,136],"data":[111],"for":[112],"training":[113,137],"polish":[115],"our":[116],"model.":[117],"Experimental":[118],"results":[119],"indicate":[120],"that":[121],"RNN":[124],"takes":[127],"advantage":[128],"scheme,":[132],"especially":[133],"data,":[138],"higher":[141],"F1-measure":[142],"compared":[143],"conventional":[145],"state-of-the-art":[146],"methods.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}