Model architectures to extrapolate emotional expressions in DNN-based text-to-speech

TL;DR

This paper introduces novel DNN architectures for emotional speech synthesis that can extrapolate emotional expressions without needing emotional speech data from target speakers, enabling flexible and efficient emotional TTS.

Contribution

The study proposes multiple architectures to separately model speaker and emotional features, allowing emotional expression transfer without target speaker emotional speech data.

Findings

Subjective evaluations show the models can convey emotions to some extent.

The parallel model (PM) correctly conveys sad and joyful emotions over 60%.

Objective evaluations are inconclusive due to variability in emotional expression.

Abstract

This paper proposes architectures that facilitate the extrapolation of emotional expressions in deep neural network (DNN)-based text-to-speech (TTS). In this study, the meaning of "extrapolate emotional expressions" is to borrow emotional expressions from others, and the collection of emotional speech uttered by target speakers is unnecessary. Although a DNN has potential power to construct DNN-based TTS with emotional expressions and some DNN-based TTS systems have demonstrated satisfactory performances in the expression of the diversity of human speech, it is necessary and troublesome to collect emotional speech uttered by target speakers. To solve this issue, we propose architectures to separately train the speaker feature and the emotional feature and to synthesize speech with any combined quality of speakers and emotions. The architectures are parallel model (PM), serial model (SM), auxiliary input model (AIM), and hybrid models (PM&AIM and SM&AIM). These models are trained through emotional speech uttered by few speakers and neutral speech uttered by many speakers. Objective evaluations demonstrate that the performances in the open-emotion test provide insufficient information. They make a comparison with those in the closed-emotion test, but each speaker has their own manner of expressing emotion. However, subjective evaluation results indicate that the proposed models could convey emotional information to some extent. Notably, the PM can correctly convey sad and joyful emotions at a rate of >60%.