3 datasets found

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate...

Text-to-speech (TTS) models have achieved remarkable naturalness in recent years, yet like most deep neural models, they have more parameters than necessary. Sparse TTS models...

A popular text-based VC approach is to use an automatic speech recognition (ASR) model to extract phonetic posteriorgram (PPG) as content representation.