Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems

Autor:	Yoon, Hyun-Wook, Kwon, Ohsung, Lee, Hoyeon, Yamamoto, Ryuichi, Song, Eunwoo, Kim, Jae-Min, Hwang, Min-Jae
Rok vydání:	2022
Předmět:	Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by INTERSPEECH2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2206.15067 Zobrazit plný text záznamu View this record from Arxiv