{"id":"https://openalex.org/W4403791945","doi":"https://doi.org/10.1145/3664647.3680669","title":"SpeechEE: A Novel Benchmark for Speech Event Extraction","display_name":"SpeechEE: A Novel Benchmark for Speech Event Extraction","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791945","doi":"https://doi.org/10.1145/3664647.3680669"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5112118387","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-4474-3047"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meishan Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055815455","display_name":"Hao Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Fei","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029336400","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0001-8714-4151"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922939","display_name":"Bobo Li","orcid":"https://orcid.org/0000-0002-0513-5540"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bobo Li","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089517967","display_name":"Shengqiong Wu","orcid":"https://orcid.org/0000-0001-6192-1194"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengqiong Wu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5112118387"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16804187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10449","last_page":"10458"},"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":0.9987000226974487,"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":0.9980000257492065,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7902119159698486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7297622561454773},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5922620296478271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5657538175582886},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5438351035118103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37765881419181824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3643377125263214},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06399759650230408}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7902119159698486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297622561454773},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5922620296478271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5657538175582886},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5438351035118103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37765881419181824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3643377125263214},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06399759650230408},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2163107094","https://openalex.org/W2187089797","https://openalex.org/W2250575108","https://openalex.org/W2250999640","https://openalex.org/W2475245295","https://openalex.org/W2508618307","https://openalex.org/W2738829388","https://openalex.org/W2801798988","https://openalex.org/W2892025684","https://openalex.org/W2914304175","https://openalex.org/W2914417638","https://openalex.org/W2952437275","https://openalex.org/W2964243274","https://openalex.org/W2984582583","https://openalex.org/W2998286882","https://openalex.org/W3034184697","https://openalex.org/W3034900014","https://openalex.org/W3035229828","https://openalex.org/W3099832538","https://openalex.org/W3103519070","https://openalex.org/W3153491684","https://openalex.org/W3170759063","https://openalex.org/W3174945605","https://openalex.org/W3175824375","https://openalex.org/W3209059054","https://openalex.org/W4205157616","https://openalex.org/W4212774754","https://openalex.org/W4212926911","https://openalex.org/W4226103796","https://openalex.org/W4226470037","https://openalex.org/W4283271696","https://openalex.org/W4283749766","https://openalex.org/W4287019595","https://openalex.org/W4365600875","https://openalex.org/W4375928968","https://openalex.org/W4385567273","https://openalex.org/W4385569940","https://openalex.org/W4385570514","https://openalex.org/W4385570685","https://openalex.org/W4385573272","https://openalex.org/W4387968266","https://openalex.org/W4387969604","https://openalex.org/W4396759399","https://openalex.org/W4402753940"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Event":[0],"extraction":[1],"(EE)":[2],"is":[3],"a":[4,72,83,95,158,164,185],"critical":[5],"direction":[6],"in":[7,143],"the":[8,18,68,77,89,105,125,140,144,154,178,181,189,194,212],"field":[9],"of":[10,20,180],"information":[11,45],"extraction,":[12],"laying":[13],"an":[14,148],"important":[15],"foundation":[16],"for":[17,33,188,206],"construction":[19],"structured":[21],"knowledge":[22],"bases.":[23],"EE":[24,59,102],"from":[25,47,60,82],"text":[26],"has":[27,62],"received":[28],"ample":[29],"research":[30],"and":[31,80,108,121,133,163,211],"attention":[32],"years,":[34],"yet":[35],"there":[36],"can":[37],"be":[38],"numerous":[39],"real-world":[40],"applications":[41],"that":[42],"require":[43],"direct":[44],"acquisition":[46],"speech":[48,61],"signals,":[49],"online":[50],"meeting":[51],"minutes,":[52],"interview":[53],"summaries,":[54],"press":[55],"releases,":[56],"etc.":[57],"While":[58],"remained":[63],"under-explored,":[64],"this":[65,198],"paper":[66],"fills":[67],"gap":[69],"by":[70],"pioneering":[71],"SpeechEE,":[73],"defined":[74],"as":[75],"detecting":[76],"event":[78],"predicates":[79],"arguments":[81],"given":[84],"audio":[85],"speech.":[86],"To":[87],"benchmark":[88,213],"SpeechEE":[90,150,175],"task,":[91,145],"we":[92,111,146,200],"first":[93,195],"construct":[94],"large-scale":[96],"high-quality":[97],"dataset.":[98],"Based":[99],"on":[100,153,173,197,203],"textual":[101],"datasets":[103,214],"under":[104],"sentence,":[106],"document,":[107],"dialogue":[109],"scenarios,":[110,129],"convert":[112],"texts":[113],"into":[114],"speeches":[115],"through":[116],"both":[117],"manual":[118],"real-person":[119],"narration":[120],"automatic":[122],"synthesis,":[123],"empowering":[124],"data":[126],"with":[127],"diverse":[128],"languages,":[130],"domains,":[131],"ambiences,":[132],"speaker":[134],"styles.":[135],"Further,":[136],"to":[137],"effectively":[138],"address":[139],"key":[141,204],"challenges":[142],"tailor":[147],"E2E":[149],"system":[151],"based":[152],"encoder-decoder":[155],"architecture,":[156],"where":[157],"novel":[159],"Shrinking":[160],"Unit":[161],"module":[162],"retrieval-aided":[165],"decoding":[166],"mechanism":[167],"are":[168,215],"devised.":[169],"Extensive":[170],"experimental":[171],"results":[172],"all":[174],"subsets":[176],"demonstrate":[177],"efficacy":[179],"proposed":[182],"model,":[183],"offering":[184],"strong":[186],"baseline":[187],"task.":[190],"At":[191],"last,":[192],"being":[193],"work":[196],"topic,":[199],"shed":[201],"light":[202],"directions":[205],"future":[207],"research.":[208],"Our":[209],"codes":[210],"open":[216],"at":[217],"https://SpeechEE.github.io/":[218]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}