{"id":"https://openalex.org/W2944569409","doi":"https://doi.org/10.1109/iscslp.2018.8706625","title":"Emphasis Detection for Voice Dialogue Applications Using Multi-channel Convolutional Bidirectional Long Short-Term Memory Network","display_name":"Emphasis Detection for Voice Dialogue Applications Using Multi-channel Convolutional Bidirectional Long Short-Term Memory Network","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944569409","doi":"https://doi.org/10.1109/iscslp.2018.8706625","mag":"2944569409"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100363496","display_name":"Long Zhang","orcid":"https://orcid.org/0000-0001-7877-7993"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Long Zhang","raw_affiliation_strings":["Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705259","display_name":"Fanbo Meng","orcid":"https://orcid.org/0009-0008-1576-3074"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanbo Meng","raw_affiliation_strings":["Beijing Sogou Technology Co. Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Sogou Technology Co. Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101482021","display_name":"Suping Zhou","orcid":"https://orcid.org/0000-0002-3472-1434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suping Zhou","raw_affiliation_strings":["Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344522","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-0065-3610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Beijing Sogou Technology Co. Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Sogou Technology Co. Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004050882","display_name":"Cunjun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cunjun Zhang","raw_affiliation_strings":["Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031445347","display_name":"Runnan Li","orcid":"https://orcid.org/0000-0002-9833-6105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runnan Li","raw_affiliation_strings":["Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100363496"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6816,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79165566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"210","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","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":0.8036479353904724},{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.7963957786560059},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6912047266960144},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.645149827003479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6021075248718262},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5912075042724609},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5587836503982544},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5133001208305359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4107295274734497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3421506881713867},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2913040518760681},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10932013392448425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036479353904724},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.7963957786560059},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6912047266960144},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.645149827003479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6021075248718262},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5912075042724609},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5587836503982544},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5133001208305359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4107295274734497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3421506881713867},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2913040518760681},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10932013392448425},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W61851215","https://openalex.org/W959948017","https://openalex.org/W1509691205","https://openalex.org/W1509956201","https://openalex.org/W1531333757","https://openalex.org/W1975343484","https://openalex.org/W2022282254","https://openalex.org/W2049950192","https://openalex.org/W2074818733","https://openalex.org/W2125689567","https://openalex.org/W2131774270","https://openalex.org/W2133693888","https://openalex.org/W2153635508","https://openalex.org/W2191779130","https://openalex.org/W2242221029","https://openalex.org/W2280620570","https://openalex.org/W2284289336","https://openalex.org/W2294797155","https://openalex.org/W2326822427","https://openalex.org/W2405329321","https://openalex.org/W2408160348","https://openalex.org/W2508492018","https://openalex.org/W2514588627","https://openalex.org/W2518591046","https://openalex.org/W2591794820","https://openalex.org/W2604735539","https://openalex.org/W2697504846","https://openalex.org/W2747920239","https://openalex.org/W2788776247","https://openalex.org/W2963625095","https://openalex.org/W2964083648","https://openalex.org/W4285719527","https://openalex.org/W6625216415","https://openalex.org/W6630351916","https://openalex.org/W6630475647","https://openalex.org/W6656079163","https://openalex.org/W6669213532","https://openalex.org/W6679901780","https://openalex.org/W6685810106","https://openalex.org/W6695662000","https://openalex.org/W6696843773","https://openalex.org/W6713644238","https://openalex.org/W6748363073"],"related_works":["https://openalex.org/W2055105357","https://openalex.org/W2153819599","https://openalex.org/W2255426644","https://openalex.org/W2072124641","https://openalex.org/W2167093538","https://openalex.org/W2018956713","https://openalex.org/W2081479354","https://openalex.org/W2113107605","https://openalex.org/W3204693335","https://openalex.org/W1971573522"],"abstract_inverted_index":{"Emphasis":[0],"detection":[1],"is":[2],"important":[3],"for":[4,105],"user":[5],"intention":[6],"understanding":[7],"in":[8,21,27,52,93,131],"human-computer":[9],"interaction":[10],"scenario.":[11],"Techniques":[12],"have":[13],"been":[14],"developed":[15],"to":[16,48,97],"detect":[17,50],"the":[18,32,94],"emphatic":[19],"words":[20],"speech,":[22],"but":[23],"challenges":[24],"still":[25],"exist":[26],"Voice":[28,123],"Dialogue":[29],"Applications":[30],"(VDAs):":[31],"tremendous":[33],"non-specific":[34],"speakers":[35,75],"and":[36,76],"their":[37],"various":[38,69],"expressions.":[39],"In":[40,84],"this":[41],"work,":[42],"we":[43,86],"present":[44],"a":[45,89,112],"novel":[46],"approach":[47,96],"automatically":[49],"emphasis":[51,106],"VDAs":[53],"by":[54],"using":[55],"multi-channel":[56,90],"convolutional":[57,91],"bi":[58],"-directional":[59],"long":[60,77],"short-term":[61],"memory":[62],"neural":[63],"networks":[64],"(MC-BLSTM),":[65],"which":[66],"can":[67],"learn":[68],"expressions":[70],"of":[71,74,101,133],"large":[72],"amounts":[73],"span":[78],"temporal":[79],"dependencies":[80],"across":[81],"speech":[82],"trajectories.":[83],"particular,":[85],"first":[87],"use":[88],"component":[92],"proposed":[95],"extract":[98],"high-level":[99],"representation":[100],"input":[102],"acoustic":[103],"features":[104],"detection.":[107],"The":[108],"experimental":[109],"results":[110],"on":[111,135],"3400":[113],"real-world":[114],"dataset":[115],"collected":[116],"from":[117],"Sogou":[118],"<sup":[119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">11</sup>":[121],"http://yy.sogou.com":[122],"Assistant":[124],"outper-form":[125],"current":[126],"state-of-the-art":[127],"baseline":[128],"systems":[129],"(+6.2%":[130],"terms":[132],"F1-measure":[134],"average).":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}