Attention-based Wav2Text with Feature Transfer Learning

22 Sep 2017Andros TjandraSakriani SaktiSatoshi Nakamura

Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier stage can propagate through the later stages... (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.