11 citations · 12 across the 4 of their papers we have counts for
4 papers
Building Tailored Speech Recognizers for Japanese Speaking Assessment
Yotaro Kubo, Richard Sproat, Chihiro Taguchi +1
This paper presents methods for building speech recognizers tailored for Japanese speaking assessment tasks. Specifically, we build a speech recognizer that outputs phonemic labels…
Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers
Yotaro Kubo, Shigeki Karita, Michiel Bacchiani
End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a si…
A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition
Shigeki Karita, Yotaro Kubo, Michiel Adriaan Unico Bacchiani +1
End-to-end (E2E) modeling is advantageous for automatic speech recognition (ASR) especially for Japanese since word-based tokenization of Japanese is not trivial, and E2E modeling…
Compacting Neural Network Classifiers via Dropout Training
Yotaro Kubo, George Tucker, Simon Wiesler
We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization…