Emotion Intensity and its Control for Emotional Voice Conversion
This work addresses the need for more nuanced emotional expression in speech synthesis for applications like human-computer interaction, though it is incremental in extending existing EVC methods.
The paper tackles the problem of controlling fine-grained emotion intensity in emotional voice conversion, which typically treats emotions as discrete categories, and demonstrates through evaluations that the proposed network effectively controls emotion intensity in output speech.
Emotional voice conversion (EVC) seeks to convert the emotional state of an utterance while preserving the linguistic content and speaker identity. In EVC, emotions are usually treated as discrete categories overlooking the fact that speech also conveys emotions with various intensity levels that the listener can perceive. In this paper, we aim to explicitly characterize and control the intensity of emotion. We propose to disentangle the speaker style from linguistic content and encode the speaker style into a style embedding in a continuous space that forms the prototype of emotion embedding. We further learn the actual emotion encoder from an emotion-labelled database and study the use of relative attributes to represent fine-grained emotion intensity. To ensure emotional intelligibility, we incorporate emotion classification loss and emotion embedding similarity loss into the training of the EVC network. As desired, the proposed network controls the fine-grained emotion intensity in the output speech. Through both objective and subjective evaluations, we validate the effectiveness of the proposed network for emotional expressiveness and emotion intensity control.