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 …

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is
important to capture the diversity in human speech such as speaker identities, prosodies …

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in
achieving timbre and speech style generalization, particularly in zero-shot TTS. However …

Neural text-to-speech (TTS) generally consists of cascaded architecture with separately
optimized acoustic model and vocoder, or end-to-end architecture with continuous mel …

Abstract Machine learning methods for conditional data generation usually build a mapping
from source conditional data X to target data Y. The target Y (eg, text, speech, music, image …

Despite rapid progress in the voice style transfer (VST) field, recent zero-shot VST systems
still lack the ability to transfer the voice style of a novel speaker. In this paper, we present …

There has been a growing interest in using end-to-end acoustic models for singing voice
synthesis (SVS). Typically, these models require an additional vocoder to transform the …

As a type of biometric identification, speaker identification (SID) systems face various
attacks. Spoofing attacks imitate target speakers' timbre, while adversarial attacks confuse …

The vulnerability of the speaker identity verification system to attacks using voice cloning
was examined. The research project assumed creating a model for verifying the speaker's …

Recent anti-spoofing systems focus on spoofing detection, where the task is only to
determine whether the test audio is fake. However, there are few studies putting attention to …