EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cho, Deok-Hyeon, Oh, Hyung-Seok, Kim, Seung-Bin, Lee, Seong-Whan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917987297001472
author Cho, Deok-Hyeon
Oh, Hyung-Seok
Kim, Seung-Bin
Lee, Seong-Whan
author_facet Cho, Deok-Hyeon
Oh, Hyung-Seok
Kim, Seung-Bin
Lee, Seong-Whan
contents Emotional text-to-speech (TTS) technology has achieved significant progress in recent years; however, challenges remain owing to the inherent complexity of emotions and limitations of the available emotional speech datasets and models. Previous studies typically relied on limited emotional speech datasets or required extensive manual annotations, restricting their ability to generalize across different speakers and emotional styles. In this paper, we present EmoSphere++, an emotion-controllable zero-shot TTS model that can control emotional style and intensity to resemble natural human speech. We introduce a novel emotion-adaptive spherical vector that models emotional style and intensity without human annotation. Moreover, we propose a multi-level style encoder that can ensure effective generalization for both seen and unseen speakers. We also introduce additional loss functions to enhance the emotion transfer performance for zero-shot scenarios. We employ a conditional flow matching-based decoder to achieve high-quality and expressive emotional TTS in a few sampling steps. Experimental results demonstrate the effectiveness of the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02625
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector
Cho, Deok-Hyeon
Oh, Hyung-Seok
Kim, Seung-Bin
Lee, Seong-Whan
Sound
Artificial Intelligence
Audio and Speech Processing
Emotional text-to-speech (TTS) technology has achieved significant progress in recent years; however, challenges remain owing to the inherent complexity of emotions and limitations of the available emotional speech datasets and models. Previous studies typically relied on limited emotional speech datasets or required extensive manual annotations, restricting their ability to generalize across different speakers and emotional styles. In this paper, we present EmoSphere++, an emotion-controllable zero-shot TTS model that can control emotional style and intensity to resemble natural human speech. We introduce a novel emotion-adaptive spherical vector that models emotional style and intensity without human annotation. Moreover, we propose a multi-level style encoder that can ensure effective generalization for both seen and unseen speakers. We also introduce additional loss functions to enhance the emotion transfer performance for zero-shot scenarios. We employ a conditional flow matching-based decoder to achieve high-quality and expressive emotional TTS in a few sampling steps. Experimental results demonstrate the effectiveness of the proposed framework.
title EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2411.02625