Some new papers (from INTERSPEECH 2020)

Thought I’d mention that INTERSPEECH 2020 just announced their list of accepted papers in the technical program.

A number of them relate to TTS, and although the technical program page above doesn’t have direct links to the papers, it looks like many are available on Arxiv if you use this query:"INTERSPEECH+2020"+synthesis&searchtype=all&abstracts=show&order=-announced_date_first&size=50


The year of the vocoder?

there is a paper “Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions” but we already proves that you don’t need speaker conditioning for it to work. :slight_smile:

this also looks interesting and easy to implement with our repo