# Emotional Voice Conversion With Cycle-consistent Adversarial Network

arXiv: https://arxiv.org/abs/2004.03781 · HTML: https://mlsanity.com/paper/2004.03781/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era](https://mlsanity.com/paper/2210.03538/) (2022)
- [Nonparallel Emotional Voice Conversion For Unseen Speaker-Emotion Pairs Using Dual Domain Adversarial Network & Virtual Domain Pairing](https://mlsanity.com/paper/2302.10536/) (2023)
- [CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer](https://mlsanity.com/paper/2111.15159/) (2021)
- [Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness](https://mlsanity.com/paper/2404.06714/) (2024)
- [The Tug-of-War Between Deepfake Generation and Detection](https://mlsanity.com/paper/2407.06174/) (2024)

## Abstract (arXiv)

Emotional Voice Conversion, or emotional VC, is a technique of converting speech from one emotion state into another one, keeping the basic linguistic information and speaker identity. Previous approaches for emotional VC need parallel data and use dynamic time warping (DTW) method to temporally align the source-target speech parameters. These approaches often define a minimum generation loss as the objective function, such as L1 or L2 loss, to learn model parameters. Recently, cycle-consistent generative adversarial networks (CycleGAN) have been used successfully for non-parallel VC. This paper investigates the efficacy of using CycleGAN for emotional VC tasks. Rather than attempting to learn a mapping between parallel training data using a frame-to-frame minimum generation loss, the CycleGAN uses two discriminators and one classifier to guide the learning process, where the discriminators aim to differentiate between the natural and converted speech and the classifier aims to classify the underlying emotion from the natural and converted speech. The training process of the CycleGAN models randomly pairs source-target speech parameters, without any temporal alignment operation. The objective and subjective evaluation results confirm the effectiveness of using CycleGAN models for emotional VC. The non-parallel training for a CycleGAN indicates its potential for non-parallel emotional VC.