Synthetic realities are digital creations or augmentations that are contextually generated
through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data …

While recent large-scale neural codec language models have shown significant
improvement in zero-shot TTS by training on thousands of hours of data, they suffer from …

The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens,
has been proven superior to traditional acoustic feature mel-spectrograms in terms of …

The rise of audio deepfakes presents a significant security threat that undermines trust in
digital communications and media. These synthetic audio technologies can convincingly …

We propose Easy End-to-End Diffusion-based Text to Speech, a simple and efficient end-to-
end text-to-speech model based on diffusion. E3 TTS directly takes plain text as input and …

Although diffusion models in text-to-speech have become a popular choice due to their
strong generative ability, the intrinsic complexity of sampling from diffusion models harms …

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective
method for improving the diversity and naturalness of synthesized speech. At the high level …

Audio captioning, a comprehensive task of audio understanding, aims to provide a natural-
language description of an audio clip. Beyond accuracy, diversity is also a critical …

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate
human speech's diversity, including unique speaker identities and linguistic nuances …

The field of brain-to-stimuli reconstruction has seen significant progress in the last few years,
but techniques continue to be subject-specific and are usually tested on a single dataset. In …