Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models

被引:0
作者
Meng, Zhao [1 ,2 ,3 ]
Mou, Lili [1 ,2 ,4 ]
Jin, Zhi [1 ,2 ]
机构
[1] Peking Univ, MoE, Key Lab High Confidence Software Technol, Beijing, Peoples R China
[2] Peking Univ, Software Inst, Beijing, Peoples R China
[3] Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland
[4] Univ Waterloo, David R Cheriton Sch Comp Sci, Waterloo, ON, Canada
来源
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | 2018年
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we address the problem of speaker classification in multi-party conversation, and collect massive data to facilitate research in this direction. We further investigate temporal-based and content-based models of speakers, and propose several hybrids of them. Experiments show that speaker classification is feasible, and that hybrid models outperform each single component.(1)
引用
收藏
页码:8121 / 8122
页数:2
相关论文
共 7 条
[1]   Speaker Diarization: A Review of Recent Research [J].
Anguera Miro, Xavier ;
Bozonnet, Simon ;
Evans, Nicholas ;
Fredouille, Corinne ;
Friedland, Gerald ;
Vinyals, Oriol .
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (02) :356-370
[2]  
[Anonymous], 2018, AAAI
[3]   Hybrid computing using a neural network with dynamic external memory [J].
Graves, Alex ;
Wayne, Greg ;
Eynolds, Malcolm R. ;
Harley, Tim ;
Danihelka, Ivo ;
Grabska-Barwinska, Agnieszka ;
Colmenarejo, Sergio Gomez ;
Grefenstette, Edward ;
Amalho, Tiago R. ;
Agapiou, John ;
Badia, Adria Puigdomenech ;
Hermann, Karl Moritz ;
Zwols, Yori ;
Strovski, Georg O. ;
Ain, Adam C. ;
King, Helen ;
Summerfield, Christopher ;
Lunsom, Phil B. ;
Kavukcuoglu, Koray ;
Hassabis, Demis .
NATURE, 2016, 538 (7626) :471-+
[4]  
Li JW, 2016, PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, P994
[5]  
Lin G.I., 2011, Proceedings of the Seventh AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, P46
[6]  
Lowe Ryan, 2015, P 16 ANN M SPEC INT, P285, DOI DOI 10.18653/V1/W15-4640
[7]  
Rocktaschel T., 2016, P 4 INT C LEARN REPR