research
∙
07/31/2023
Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Neural text-to-speech systems are often optimized on L1/L2 losses, which...
share
research
∙
07/04/2022
GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
In this paper, we propose GlowVC: a multilingual multi-speaker flow-base...
research
∙
06/28/2022
Expressive, Variable, and Controllable Duration Modelling in TTS
Duration modelling has become an important research problem once more wi...
research
∙
03/15/2022
Text-free non-parallel many-to-many voice conversion using normalising flows
Non-parallel voice conversion (VC) is typically achieved using lossy rep...
research
∙
06/24/2021
Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Whilst recent neural text-to-speech (TTS) approaches produce high-qualit...
research
∙
11/11/2020
Low-resource expressive text-to-speech using data augmentation
While recent neural text-to-speech (TTS) systems perform remarkably well...
research
∙
04/04/2019
In Other News: A Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data
Neural text-to-speech synthesis (NTTS) models have shown significant pro...
research
∙
11/15/2018
Effect of data reduction on sequence-to-sequence neural TTS
Recent speech synthesis systems based on sampling from autoregressive ne...
research
∙
11/15/2018
Comprehensive evaluation of statistical speech waveform synthesis
Statistical TTS systems that directly predict the speech waveform have r...
research
∙
11/15/2018
Robust universal neural vocoding
This paper introduces a robust universal neural vocoder trained with 74 ...
research
∙
07/28/2018