Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody. (arXiv:2206.14643v1 [eess.AS])

Generating expressive and contextually appropriate prosody remains a
challenge for modern text-to-speech (TTS) systems. This is particularly evident
for long, multi-sentence inputs. In this paper, we examine simple extensions to
a Transformer-based FastSpeech-like system, with the goal of improving prosody
for multi-sentence TTS. We find that long context, powerful text features, and
training on multi-speaker data all improve prosody. More interestingly, they
result in synergies. Long context disambiguates prosody, improves coherence,
and plays to the strengths of Transformers. Fine-tuning word-level …

arxiv tts