Recent advancements in generative speech models based on audio-text prompts have
enabled remarkable innovations like high-quality zero-shot text-to-speech. However …

Speaker individuality information is among the most critical elements within speech signals.
By thoroughly and accurately modeling this information, it can be utilized in various …

Language models have been effectively applied to modeling natural signals, such as
images, video, speech, and audio. A crucial component of these models is the codec …

Neural audio codec models are becoming increasingly important as they serve as
tokenizers for audio, enabling efficient transmission or facilitating speech language …

The task of the challenge is to develop a voice anonymization system for speech data which
conceals the speaker's voice identity while protecting linguistic content and emotional states …

We present MELLE, a novel continuous-valued tokens based language modeling approach
for text to speech synthesis (TTS). MELLE autoregressively generates continuous mel …

Amphion is an open-source toolkit for Audio, Music, and Speech Generation, targeting to
ease the way for junior researchers and engineers into these fields. It presents a unified …

This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-
autoregressive zero-shot text-to-speech system that offers human-level naturalness and …

This paper introduces F5-TTS, a fully non-autoregressive text-to-speech system based on
flow matching with Diffusion Transformer (DiT). Without requiring complex designs such as …

Recent advancements in speech generation models have been significantly driven by the
use of large-scale training data. However, producing highly spontaneous, human-like …