2023· Tecniacústica 2023 · XIII Congreso Ibérico de Acústica· pp. 735-742· 0 citations
TL;DR
A preliminary comparative study of various neural models applied to emotional voice conversion explores the performance of state-of-the-art models: seq2seq-EVC and CycleGAN-EVC and assess the perceptual quality of the converted emotional voice using subjective metrics, providing a complete view of model performance.
Abstract
Emotional voice conversion (EVC) is a fundamental task in the field of speech processing, enabling the modification of the emotional content of a spoken message while preserving the speaker's identity. This article presents a preliminary comparative study of various neural models applied to emotional voice conversion. We explore the performance of state-of-the-art models: seq2seq-EVC and CycleGAN-EVC. To do so, we evaluate these models on various emotional datasets and analyze their ability to accurately convert emotions across a spectrum of affective states. Our preliminary experiments reveal insights into the strengths and limitations of each neural model in capturing and transferring emotional nuances in speech. We discuss key factors such as model architecture, dataset size, and training strategies, shedding light on the trade-offs between computational complexity and conversion quality. Additionally, we assess the perceptual quality of the converted emotional voice using subjective metrics, providing a complete view of model performance.
This study compares three ways of representing speech using Mel-Frequency Cepstral Coefficients: 13, 26, and 39 coefficients, and identifies MFCC-39 as the most promising of the three variants and MFCC-13 as a lighter baseline.
N. S. Patil Dr, S. G. Deeksha, R. Harsha et al.· Indian Journal of Computer S...· 0 citations
ACERT (Averaged Contextual Emotion Representation through Time), a module that integrates a flexible-length window of conversational context to better capture emotional evolution in spoken interactions, is introduced.
Arthur Peuvot, Romaric Besançon, Gaël de Chalendar et al.· arXiv.org· 0 citations
Recent diffusion- and conditional flow matching (CFM)-based emotional voice conversion (EVC) systems achieve strong conversion quality. However, they typically rely on multiple sampling steps, because the conditioning specifies which emotion to impose while its acoustic realization is left to the sampler. In this paper...
Yu Pan, Xiao-Juan Cai, Liang Zhang et al.· 0 citations
Speech Emotion Recognition SER has become a widely studied issue in the circle of affective computing. It has been used in human-computer interaction and neuropsychology. In the current research, deep learning methodologies-based models are constructed for artificial intelligence integration into SER systems. We use th...
Ashok Gupta Maturi, T. Krishnan· Adolescência e Saúde· 0 citations
This paper introduces VoiceNet, a human-annotated representation-level benchmark for voice performance understanding on permissively-licensed in-the-wild speech, and releases Emolia, an emotion-annotated version of the Emilia corpus, with a curated rebalanced subset enriched by dense MOSS-Audio Thinking annotations.
Christoph Schuhmann, R. Kaczmarczyk, Gollam Rabby et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.