Hiroshi Seki — accepted AI-conference papers

2018

An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech

Hiroshi Seki, Shinji Watanabe, Takaaki Hori, Jonathan Le Roux, John R. Hershey

ICASSP 2018accepted

End-to-end automatic speech recognition (ASR) can significantly reduce the burden of developing ASR systems for new languages, by eliminating the need for linguistic information such as pronunciation dictionaries. This also creates an opportunity to build a monolithic multilingual ASR system with a…

Cited by 0 Source ↗Scholar ↗

2017

A deep neural network integrated with filterbank learning for speech recognition

Hiroshi Seki, Kazumasa Yamamoto, Seiichi Nakagawa

ICASSP 2017accepted

Deep neural networks (DNN) have achieved significant success in the field of speech recognition. One of the main advantages of the DNN is automatic feature extraction without human intervention. Therefore, we incorporate a pseudo-filterbank layer to the bottom of DNN and train the whole filterbank l…

Cited by 0 Source ↗Scholar ↗