Libri-Light: A Benchmark for ASR with Limited or No Supervision

17 Dec 2019Jacob KahnMorgane RivièreWeiyi ZhengEvgeny KharitonovQiantong XuPierre-Emmanuel MazaréJulien KaradayiVitaliy LiptchinskyRonan CollobertChristian FuegenTatiana LikhomanenkoGabriel SynnaeveArmand JoulinAbdelrahman MohamedEmmanuel Dupoux

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project... (read more)

PDF Abstract

Evaluation 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.