Guest Editorial: Special Issue on Affective Speech and Language Synthesis, Generation, and Conversion

被引:3
|
作者
Amiriparian, Shahin [1 ]
Schuller, Bjoern W. [1 ,2 ,6 ]
Asghar, Nabiha [3 ]
Zen, Heiga [4 ]
Burkhardt, Felix [5 ,6 ]
机构
[1] Univ Augsburg, Embedded Intelligence Hlth Care & Wellbeing, D-86159 Augsburg, Germany
[2] Imperial Coll London, GLAM Grp Language Audio & Music, London SW7 2BX, England
[3] Microsoft, Redmond, WA 98052 USA
[4] Google Res, Tokyo 1050004, Japan
[5] Tech Univ Berlin, Speech Commun, D-10623 Berlin, Germany
[6] audEERING GmbH, D-82205 Gilching, Germany
关键词
Special issues and sections; Affective computing; Speech recognition; Oral communication; Emotion recognition; Real-time systems; Natural language processing; Human computer interaction; Artificial intelligence; Trust computing; Training data; Emotion synthesis; emotion conversion; human-AI interaction; empathic AI; affective computing;
D O I
10.1109/TAFFC.2022.3233120
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The papers in this special section focus on affective speech and language synthesis, generation, and conversion. As an inseparable and crucial part of spoken language, emotions play a substantial role in human-human and human-technology conversation. They convey information about a person's needs, how one feels about the objectives of a conversation, the trustworthiness of one's verbal communication, and more. Accordingly, substantial efforts have been made to generate affective text and speech for conversational AI, artificial storytelling, and machine translation. Similarly, there is a push for converting the affect in text and speech, ideally, in real-time and fully preserving intelligibility, e. g., to hide one's emotion, for creative applications and in entertainment, or even to augment training data for affect analyzing AI.
引用
收藏
页码:3 / 5
页数:3
相关论文
共 50 条