Hacker News new | comments | show | ask | jobs | submit login

Absolutely - listening through the multiple samples with different intonation from both Obama and Trump, some of the samples are much more realistic, while others come off as robotic.

Maybe it would be possible to train the system to prefer certain intonations in certain cases by rating the realism of the speech in context. It would be interesting to analyzes pauses around words grouped by word2vec! Or choosing a "style" of intonations based on punctuation, parameters like words/minute, etc.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact