We propose PromptTTS++, a prompt-based text-to-speech (TTS) synthesis sy...
We propose ChatGPT-EDSS, an empathetic dialogue speech synthesis (EDSS)
...
We present CALLS, a Japanese speech corpus that considers phone calls in...
We propose a lightweight end-to-end text-to-speech model using multi-ban...
Several fully end-to-end text-to-speech (TTS) models have been proposed ...
Neural audio super-resolution models are typically trained on low- and
h...
We propose an end-to-end empathetic dialogue speech synthesis (DSS) mode...
Data augmentation via voice conversion (VC) has been successfully applie...
Most text-to-speech (TTS) methods use high-quality speech corpora record...
We present STUDIES, a new speech corpus for developing a voice agent tha...
We propose a novel phrase break prediction method that combines implicit...
We propose Progressive Structure-conditional Generative Adversarial Netw...