EMOQ-TTS: Emotion Intensity Quantization for Fine-Grained Controllable Emotional Text-to-Speech

Abstract

Although recent advances in text-to-speech (TTS) have shown significant improvement, it is still limited to emotional speech synthesis. To produce emotional speech, most works utilize emotion information extracted from emotion labels or reference audio. However, they result in monotonous emotional expression due to the utterance-level emotion conditions. In this paper, we propose EmoQ-TTS, which synthesizes expressive emotional speech by conditioning phoneme-wise emotion information with fine-grained emotion intensity. Here, the intensity of emotion information is rendered by distance-based intensity quantization without human labeling. We can also control the emotional expression of synthesized speech by conditioning intensity labels manually. The experimental results demonstrate the superiority of EmoQ-TTS in emotional expressiveness and controllability.