TTS

nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-Shot Multi-speaker text-to-speech
Multi-speaker text-to-speech (TTS) using a few adaption data is a challenge in practical applications. To address that, we propose a …
Cite arXiv IEEE
nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-Shot Multi-speaker text-to-speech
r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled Noise Introducing and Contextual Information Incorporation
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Cite
LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation
In this paper, we propose a novel conditional convolution network, named location-variable convolution, to model the dependencies of …
Cite arXiv IEEE
LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation
GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
This paper introduces a graphical representation approach of prosody boundary (GraphPB) in the task of Chinese speech synthesis, …
Cite arXiv IEEE
GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
MelGlow: Efficient Waveform Generative Network Based On Location-Variable Convolution
Recent neural vocoders usually use a WaveNet-like network to capture the long-term dependencies of the waveform, but a large number of …
Cite arXiv IEEE
MelGlow: Efficient Waveform Generative Network Based On Location-Variable Convolution
Federated Learning with Dynamic Transformer for Text to Speech
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
PDF Cite arXiv ISCA
Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit
Recent neural speech synthesis systems have gradually focused on the control of prosody to improve the quality of synthesized speech, …
PDF Cite arXiv ISCA
Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit
Aligntts: Efficient Feed-Forward Text-to-Speech System Without Explicit Alignment
Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a …
Cite arXiv IEEE
Aligntts: Efficient Feed-Forward Text-to-Speech System Without Explicit Alignment
GraphTTS: Graph-to-Sequence Modelling in Neural Text-to-Speech
This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input …
Cite arXiv IEEE
GraphTTS: Graph-to-Sequence Modelling in Neural Text-to-Speech