Publications
CONFERENCE (INTERNATIONAL) Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems
Hyun-Wook Yoon (NAVER), Ohsung Kwon (NAVER), Hoyeon Lee (NAVER), Ryuichi Yamamoto, Eunwoo Song (NAVER), Jae-Min Kim (NAVER), Min-Jae Hwang (NAVER)
The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022)
September 18, 2022
This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method. Unlike conventional systems that require auxiliary inputs such as manually defined emotion classes, our system directly estimates emotion-related attributes from the input text. Specifically, we utilize generative pre-trained transformer (GPT)-3 to jointly predict both an emotion class and its strength in representing emotions' coarse and fine properties, respectively. Then, these attributes are combined in the emotional embedding space and used as conditional features of the TTS model for generating output speech signals. Consequently, the proposed system can produce emotional speech only from text without any auxiliary inputs. Furthermore, because the GPT-3 enables to capture emotional context among the consecutive sentences, the proposed method can effectively handle the paragraph-level generation of emotional speech.
Paper :
Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems
(external link)