The emergence of diffusion models has greatly broadened the scope of
hig...
Large language models (LLMs) with hundreds of billions of parameters sho...
In recent years, emotional text-to-speech has shown considerable progres...
Wake-up words (WUW) is a short sentence used to activate a speech recogn...
Recent advancements in autonomous technology allow for new opportunities...
This study investigates the emotional responses to the color of vehicle
...
Expressive text-to-speech has shown improved performance in recent years...
An automated design data archiving could reduce the time wasted by desig...
We present EdiTTS, an off-the-shelf speech editing methodology based on
...
This paper describes a fast speaker search system to retrieve segments o...
Although there are more than 65,000 languages in the world, the
pronunci...
We propose prosody embeddings for emotional and expressive speech synthe...
We propose a neural text-to-speech (TTS) model that can imitate a new
sp...
Artificial Neural Network computation relies on intensive vector-matrix
...