The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Deepfakes present an emerging threat in cyberspace. Recent developments in machine
learning make deepfakes highly believable, and very difficult to differentiate between what is …

While recent large-scale text-to-speech (TTS) models have achieved significant progress,
they still fall short in speech quality, similarity, and prosody. Considering speech intricately …

Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural
speech given text, is a hot research topic in speech, language, and machine learning …

Current speech large language models build upon discrete speech representations, which
can be categorized into semantic tokens and acoustic tokens. However, existing speech …

Self-supervised learning in speech involves training a speech representation network on a
large-scale unannotated speech corpus, and then applying the learned representations to …

To the best of our knowledge, we first present a live system that generates personalized
photorealistic talking-head animation only driven by audio signals at over 30 fps. Our system …

One-shot voice conversion (VC), which performs conversion across arbitrary speakers with
only a single target-speaker utterance for reference, can be effectively achieved by speech …

Given the input graph and its label/property, several key problems of graph learning, such as
finding interpretable subgraphs, graph denoising and graph compression, can be attributed …

Speech conveys more information than text, as the same word can be uttered in various
voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods …