We introduce a language modeling approach for text to speech synthesis (TTS). Specifically,
we train a neural codec language model (called Vall-E) using discrete codes derived from …

This paper introduces VALL-E 2, the latest advancement in neural codec language models
that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity …

WiFi-based Human Gesture Recognition (HGR) becomes increasingly promising for device-
free human-computer interaction. However, existing WiFi-based approaches have not been …

Personalizing a speech synthesis system is a highly desired application, where the system
can generate speech with the user's voice with rare enrolled recordings. There are two main …

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the
quality of synthesized speech for speakers in the training dataset. The challenge of …

The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common
sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning …

State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data
to generate high-quality synthetic speech. When using reduced amounts of training data …

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically,
we train a neural codec language model (called VALL-E) using discrete codes derived from …

Factorizing speech as disentangled speech representations is vital to achieve highly
controllable style transfer in voice conversion (VC). Conventional speech representation …

Zero-shot voice conversion (VC) aims to transform the source speaker timbre into an
arbitrary unseen one without altering the original speech content. While recent …