Parallel WaveNet: Fast High-Fidelity Speech Synthesis

ICML 2018 Aaron van den OordYazhe LiIgor BabuschkinKaren SimonyanOriol VinyalsKoray KavukcuogluGeorge van den DriesscheEdward LockhartLuis C. CoboFlorian StimbergNorman CasagrandeDominik GreweSeb NourySander DielemanErich ElsenNal KalchbrennerHeiga ZenAlex GravesHelen KingTom WaltersDan BelovDemis Hassabis

The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today's massively parallel computers, and therefore hard to deploy in a real-time production setting... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.