Paralinguistics in speech and language State-of-the-art and the challenge

被引:157
作者
Schuller, Bjoern [1 ]
Steidl, Stefan [2 ,3 ]
Batliner, Anton [3 ]
Burkhardt, Felix [4 ]
Devillers, Laurence [1 ,7 ]
Mueller, Christian [5 ]
Narayanan, Shrikanth [6 ]
机构
[1] CNRS LIMSI, Spoken Language Proc Grp, Orsay, France
[2] ICSI, Berkeley, CA USA
[3] Univ Erlangen Nurnberg, Pattern Recognit Lab, Nurnberg, Germany
[4] Deutsch Telekom AG, Telekom Innovat Labs, Berlin, Germany
[5] German Res Ctr Artificial Intelligence DFKI, Saarbrucken, Germany
[6] Univ So Calif, SAIL, Los Angeles, CA USA
[7] Univ Paris 04, GEMASS, Paris, France
基金
美国国家科学基金会;
关键词
Paralinguistics; Age; Gender; Affect; Survey; Trends; Challenge; EMOTION RECOGNITION; VOCAL COMMUNICATION; GENDER RECOGNITION; SLEEP-DEPRIVATION; LINGUISTIC CUES; BODY-SIZE; VOICE; PERSONALITY; SPEAKERS; CLASSIFICATION;
D O I
10.1016/j.csl.2012.02.005
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Paralinguistic analysis is increasingly turning into a mainstream topic in speech and language processing. This article aims to provide a broad overview of the constantly growing field by defining the field, introducing typical applications, presenting exemplary resources, and sharing a unified view of the chain of processing. It then presents the first broader Paralinguistic Challenge organised at INTERSPEECH 2010 by the authors including a historical overview of the Challenge tasks of recognising age, gender, and affect, a summary of methods used by the participants, and their results. In addition, we present the new benchmark obtained by fusion of participants' predictions and conclude by discussing ten recent and emerging trends in the analysis of paralinguistics in speech and language. (C) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码:4 / 39
页数:36
相关论文
共 268 条
[1]  
ABERCROMBIE D, 1968, BRIT J DISORD COMMUN, V3, P55
[2]  
Ai H, 2006, INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, P797
[3]   Vocal Telekinesis: towards the development of voice-physical installations [J].
Al Hashimi, Sama'a .
UNIVERSAL ACCESS IN THE INFORMATION SOCIETY, 2009, 8 (02) :65-75
[4]  
[Anonymous], 2010, P 11 ANN C INT SPEEC
[5]  
[Anonymous], PHONETICS L IN PRESS
[6]  
[Anonymous], 2006, THESIS U LUND SWEDEN
[7]  
[Anonymous], P IEEE INT C COMP VI
[8]  
[Anonymous], 2002, Principal components analysis
[9]  
[Anonymous], P INTERSPEECH
[10]  
[Anonymous], MOSHI SHIBIE YU RENG