research
∙
05/24/2023
LMs with a Voice: Spoken Language Modeling beyond Speech Tokens
We present SPECTRON, a novel approach to adapting pre-trained language m...
share
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...
research
∙
11/07/2021
Speaker Generation
This work explores the task of synthesizing speech in nonexistent human-...
research
∙
03/26/2021
Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
This paper introduces Parallel Tacotron 2, a non-autoregressive neural t...
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
∙
07/09/2019
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
We present a multispeaker, multilingual text-to-speech (TTS) synthesis m...
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
∙
08/30/2018
Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis
Although end-to-end text-to-speech (TTS) models such as Tacotron have sh...
research
∙
08/04/2018
Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis
Global Style Tokens (GSTs) are a recently-proposed method to learn laten...
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
∙
12/16/2017
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
This paper describes Tacotron 2, a neural network architecture for speec...
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
∙
03/29/2017