Speech Emotion Recognition Two Decades in a Nutshell, Benchmarks, and Ongoing Trends

被引:283
作者
Schuller, Bjoern W. [1 ]
机构
[1] Univ Augsburg, Embedded Intelligence Hlth Care & Wellbeing, Augsburg, Germany
关键词
FEATURES; AUDIO; VOICE; PITCH;
D O I
10.1145/3129340
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
COMMUNICATION WITH COMPUTING machinery has become increasingly 'chatty' these days: Alexa, Cortana, Siri, and many more dialogue systems have hit the consumer market on a broader basis than ever, but do any of them truly notice our emotions and react to them like a human conversational partner would? In fact, the discipline of automatically recognizing human emotion and affective states from speech, usually referred to as Speech Emotion Recognition or SER for short, has by now surpassed the "age of majority, " celebrating the 22nd anniversary after the seminal work of Daellert et al. in 199610-arguably the first research paper on the topic. However, the idea has existed even longer, as the first patent dates back to the late 1970s. © 2018 ACM.
引用
收藏
页码:90 / 99
页数:10
相关论文
共 43 条
  • [1] Abdelwahab M, 2015, INT CONF ACOUST SPEE, P5058, DOI 10.1109/ICASSP.2015.7178934
  • [2] Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011
    Anagnostopoulos, Christos-Nikolaos
    Iliou, Theodoros
    Giannoukos, Ioannis
    [J]. ARTIFICIAL INTELLIGENCE REVIEW, 2015, 43 (02) : 155 - 177
  • [3] [Anonymous], 2002, ICLSP 2002
  • [4] [Anonymous], 2013, ANALES 15 REUNION PR
  • [5] [Anonymous], 2002, Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
  • [6] [Anonymous], 2014, Proceedings of the 16th International Conference on Multimodal Interaction, DOI 10.1145/2663204.2666275
  • [7] [Anonymous], 1997, AFFECTIVE COMPUTING
  • [8] Bhaykar M., 2013, Natl Conf Commun (NCC), P1, DOI [10.1109/NCC.2013.6487998, DOI 10.1109/NCC.2013.6487998]
  • [9] THE VOICE AND THE EMOTIONS
    Blanton, Smiley
    [J]. QUARTERLY JOURNAL OF PUBLIC SPEAKING, 1915, 1 (02): : 154 - 172
  • [10] Chang J., 2017, ARXIV170502394