3 papers
eess.AS2024
VAE-based Phoneme Alignment Using Gradient Annealing and SSL Acoustic Features
Tomoki Koriyama
This paper presents an accurate phoneme alignment model that aims for speech analysis and video content creation. We propose a variational autoencoder (VAE)-based alignment model i…
cs.SD2024
An Attribute Interpolation Method in Speech Synthesis by Model Merging
Masato Murata, Koichi Miyazaki, Tomoki Koriyama
With the development of speech synthesis, recent research has focused on challenging tasks, such as speaker generation and emotion intensity control. Attribute interpolation is a c…
eess.AS2023
Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech
Dong Yang, Tomoki Koriyama, Yuki Saito +3
Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhyth…