research
∙
12/06/2022
Learning the joint distribution of two sequences using little or no paired data
We present a noisy channel generative model of two sequences, for exampl...
share
research
∙
11/07/2021
Speaker Generation
This work explores the task of synthesizing speech in nonexistent human-...
research
∙
11/06/2020
Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis
We describe a sequence-to-sequence neural network which can directly gen...
research
∙
10/15/2020
Non-saturating GAN training as divergence minimization
Non-saturating generative adversarial network (GAN) training is widely u...
research
∙
10/23/2019
Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Despite the ability to produce human-level speech for in-domain text, at...
research
∙
10/03/2019
Semi-Supervised Generative Modeling for Controllable Speech Synthesis
We present a novel generative model that combines state-of-the-art neura...
research
∙
06/08/2019
Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
Recent work has explored sequence-to-sequence latent variable models for...
research
∙
03/24/2018
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
We present an extension to the Tacotron speech synthesis architecture th...
research
∙
03/23/2018
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
In this work, we propose "global style tokens" (GSTs), a bank of embeddi...
research
∙
11/01/2017
Uncovering Latent Style Factors for Expressive Speech Synthesis
Prosodic modeling is a core problem in speech synthesis. The key challen...
research
∙
07/24/2017
Exploring Neural Transducers for End-to-End Speech Recognition
In this work, we perform an empirical comparison among the CTC, RNN-Tran...
research
∙
05/11/2017
Reducing Bias in Production Speech Models
Replacing hand-engineered pipelines with end-to-end deep learning system...
research
∙
12/08/2015