EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control

TL;DR

EmoKnob is a novel framework that enables fine-grained, emotion-controlled speech synthesis using few-shot samples, improving emotional expressiveness over existing TTS systems.

Contribution

It introduces a new emotion control method leveraging foundation voice cloning models and proposes evaluation metrics for emotional speech synthesis.

Findings

Effective emotion embedding into speech.

Surpasses commercial TTS in emotional expressiveness.

Framework supports open-ended emotion description.

Abstract

While recent advances in Text-to-Speech (TTS) technology produce natural and expressive speech, they lack the option for users to select emotion and control intensity. We propose EmoKnob, a framework that allows fine-grained emotion control in speech synthesis with few-shot demonstrative samples of arbitrary emotion. Our framework leverages the expressive speaker representation space made possible by recent advances in foundation voice cloning models. Based on the few-shot capability of our emotion control framework, we propose two methods to apply emotion control on emotions described by open-ended text, enabling an intuitive interface for controlling a diverse array of nuanced emotions. To facilitate a more systematic emotional speech synthesis field, we introduce a set of evaluation metrics designed to rigorously assess the faithfulness and recognizability of emotion control frameworks. Through objective and subjective evaluations, we show that our emotion control framework effectively embeds emotions into speech and surpasses emotion expressiveness of commercial TTS services.