eduzhai > Applied Sciences > Engineering >

Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset

  • Save

... pages left unread,continue reading

Document pages: 10 pages

Abstract: This paper presents an exploration of end-to-end automatic speech recognitionsystems (ASR) for the largest open-source Russian language data set -- OpenSTT.We evaluate different existing end-to-end approaches such as jointCTC Attention, RNN-Transducer, and Transformer. All of them are compared withthe strong hybrid ASR system based on LF-MMI TDNN-F acoustic model. For thethree available validation sets (phone calls, YouTube, and books), our bestend-to-end model achieves word error rate (WER) of 34.8 , 19.1 , and 18.1 ,respectively. Under the same conditions, the hybridASR system demonstrates33.5 , 20.9 , and 18.6 WER.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...