ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech. (arXiv:2202.07816v1 [eess.AS])

Expressive text-to-speech (TTS) has become a hot research topic recently,
mainly focusing on modeling prosody in speech. Prosody modeling has several
challenges: 1) the extracted pitch used in previous prosody modeling works have
inevitable errors, which hurts the prosody modeling; 2) different attributes of
prosody (e.g., pitch, duration and energy) are dependent on each other and
produce the natural prosody together; and 3) due to high variability of prosody
and the limited amount of high-quality data for TTS training, the …

arxiv speech text text-to-speech training