tts

AI Microsoft

AI Show Live – Custom Neural Voice, Rock-Paper-Scissors, and more!

In this live episode of the AI Show Seth will interview Edward Un about a recently GA’d feature called Custom Neural Voice. He will also continue work on his rock-paper-scissors project. Learn More: Custom Neural Voice https://aka.ms/AIShow/Speech Text-to-speech documentation https://aka.ms/AIShow/SpeechDocs Build a natural custom voice for your brand blog https://aka.ms/AIShow/CNVblog

Read More
AI

End-to-End Adversarial Text-to-Speech

Text-to-speech engines are usually multi-stage pipelines that transform the signal into many intermediate representations and require supervision at each step. When trying to train TTS end-to-end, the alignment problem arises: Which text corresponds to which piece of sound? This paper uses an alignment module to tackle this problem and produces astonishingly good sound. Paper: https://arxiv.org/abs/2006.03575 […]

Read More