Search Results for author: Satoshi Asakawa

Found 1 papers, 0 papers with code

End-to-end Adaptation with Backpropagation through WFST for On-device Speech Recognition System

no code implementations17 May 2019 Emiru Tsunoo, Yosuke Kashiwagi, Satoshi Asakawa, Toshiyuki Kumakura

We convert a pretrained WFST to a trainable neural network and adapt the system to target environments/vocabulary by E2E joint training with an AM.

speech-recognition Speech Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.