{"id":"https://openalex.org/W2970568180","doi":"https://doi.org/10.21437/interspeech.2017-407","title":"LSTM Neural Network-Based Speaker Segmentation Using Acoustic and Language Modelling","display_name":"LSTM Neural Network-Based Speaker Segmentation Using Acoustic and Language Modelling","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2970568180","doi":"https://doi.org/10.21437/interspeech.2017-407","mag":"2970568180"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-407","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085739769","display_name":"Miquel India","orcid":"https://orcid.org/0000-0002-3107-3662"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Miquel India","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004224082","display_name":"Jos\u00e9 A. R. Fonollosa","orcid":"https://orcid.org/0000-0001-9513-7939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 A.R. Fonollosa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025633053","display_name":"Javier Hernando","orcid":"https://orcid.org/0000-0002-1730-8154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Hernando","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085739769"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7552,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8901239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2834","last_page":"2838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9948999881744385,"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/T11309","display_name":"Music and Audio Processing","score":0.9801999926567078,"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":0.8279795050621033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6516651511192322},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6386429071426392},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6376050114631653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4798516631126404},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47696956992149353},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4505397379398346},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44674596190452576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279795050621033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6516651511192322},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6386429071426392},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6376050114631653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4798516631126404},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47696956992149353},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4505397379398346},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44674596190452576},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-407","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W125260059","https://openalex.org/W1556474518","https://openalex.org/W1904365287","https://openalex.org/W2075662881","https://openalex.org/W2107638917","https://openalex.org/W2125642021","https://openalex.org/W2131571251","https://openalex.org/W2150355110","https://openalex.org/W2156255174","https://openalex.org/W2402268235","https://openalex.org/W2405802804","https://openalex.org/W3146998960"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"This":[0],"paper":[2],"presents":[4],"a":[6,63,89],"new":[8],"speaker":[10,54,72,91],"change":[12],"detection":[14],"system":[16],"based":[17],"on":[18],"Long":[19],"Short-Term":[20],"Memory":[21],"(LSTM)":[22],"neural":[23,76],"networks":[24,77],"using":[26],"acoustic":[28,50,82],"data":[30],"and":[32,53,81],"linguistic":[34,80],"content.":[36],"Language":[39],"modelling":[40],"is":[41],"combined":[42],"with":[43,62,78],"two":[44],"different":[45],"Joint":[46],"Factor":[47],"Analysis":[48],"(JFA)":[49],"approaches:":[51],"i-vectors":[52],"factors.":[55],"Both":[57],"of":[58],"them":[59],"are":[60],"compared":[61],"baseline":[64,104],"algorithm":[65],"that":[66,98],"uses":[67],"cosine":[68],"distance":[69],"to":[70,87],"detect":[71],"turn":[73],"changes.":[74],"LSTM":[75],"both":[79],"features":[83],"have":[84],"been":[85],"able":[86],"produce":[88],"robust":[90],"segmentation.":[92],"The":[94],"experimental":[95],"results":[96],"show":[97],"our":[99],"proposal":[100],"clearly":[101],"outperforms":[102],"the":[103],"system.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}