Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data

6 Apr 2019 • Roee Levy Leshem • Raja Giryes

This paper introduces Taco-VC, a novel architecture for voice conversion based on Tacotron synthesizer, which is a sequence-to-sequence with attention model. The training of multi-speaker voice conversion systems requires a large number of resources, both in training and corpus size... (read more)

PDF Abstract

Results from the Paper

Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Mixture of Logistic Distributions	Output Functions
Griffin-Lim Algorithm	Phase Reconstruction
Sigmoid Activation	Activation Functions
Highway Layer	Miscellaneous Components
Residual Connection	Skip Connections
Convolution	Convolutions
Batch Normalization	Normalization
Max Pooling	Pooling Operations
Residual GRU	Recurrent Neural Networks
BiGRU	Bidirectional Recurrent Neural Networks
Highway Network	Feedforward Networks
CBHG	Speech Synthesis Blocks
ReLU	Activation Functions
Dropout	Regularization
Dense Connections	Feedforward Networks
Tanh Activation	Activation Functions
Additive Attention	Attention Mechanisms
GRU	Recurrent Neural Networks
Tacotron	Text-to-Speech Models
Dilated Causal Convolution	Temporal Convolutions
WaveNet	Generative Audio Models

METHOD

TYPE

Mixture of Logistic Distributions