EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gudmalwar, Ashishkumar, Biyani, Ishan D., Shah, Nirmesh, Wasnik, Pankaj, Shah, Rajiv Ratn
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916545296334848
author Gudmalwar, Ashishkumar
Biyani, Ishan D.
Shah, Nirmesh
Wasnik, Pankaj
Shah, Rajiv Ratn
author_facet Gudmalwar, Ashishkumar
Biyani, Ishan D.
Shah, Nirmesh
Wasnik, Pankaj
Shah, Rajiv Ratn
contents The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion intensity in the diffusion-based EVC framework to generate precise speech of the target emotion. Traditional approaches control the intensity of an emotional state in the utterance via emotion class probabilities or intensity labels that often lead to inept style manipulations and degradations in quality. On the contrary, we aim to regulate emotion intensity using self-supervised learning-based feature representations and unsupervised directional latent vector modeling (DVM) in the emotional embedding space within a diffusion-based framework. These emotion embeddings can be modified based on the given target emotion intensity and the corresponding direction vector. Furthermore, the updated embeddings can be fused in the reverse diffusion process to generate the speech with the desired emotion and intensity. In summary, this paper aims to achieve high-quality emotional intensity regularization in the diffusion-based EVC framework, which is the first of its kind work. The effectiveness of the proposed method has been shown across state-of-the-art (SOTA) baselines in terms of subjective and objective evaluations for the English and Hindi languages \footnote{Demo samples are available at the following URL: \url{https://nirmesh-sony.github.io/EmoReg/}}.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20359
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion
Gudmalwar, Ashishkumar
Biyani, Ishan D.
Shah, Nirmesh
Wasnik, Pankaj
Shah, Rajiv Ratn
Audio and Speech Processing
Artificial Intelligence
Multimedia
Sound
The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion intensity in the diffusion-based EVC framework to generate precise speech of the target emotion. Traditional approaches control the intensity of an emotional state in the utterance via emotion class probabilities or intensity labels that often lead to inept style manipulations and degradations in quality. On the contrary, we aim to regulate emotion intensity using self-supervised learning-based feature representations and unsupervised directional latent vector modeling (DVM) in the emotional embedding space within a diffusion-based framework. These emotion embeddings can be modified based on the given target emotion intensity and the corresponding direction vector. Furthermore, the updated embeddings can be fused in the reverse diffusion process to generate the speech with the desired emotion and intensity. In summary, this paper aims to achieve high-quality emotional intensity regularization in the diffusion-based EVC framework, which is the first of its kind work. The effectiveness of the proposed method has been shown across state-of-the-art (SOTA) baselines in terms of subjective and objective evaluations for the English and Hindi languages \footnote{Demo samples are available at the following URL: \url{https://nirmesh-sony.github.io/EmoReg/}}.
title EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion
topic Audio and Speech Processing
Artificial Intelligence
Multimedia
Sound
url https://arxiv.org/abs/2412.20359