Yotaro Kubo — accepted AI-conference papers

2022

Knowledge Transfer from Large-Scale Pretrained Language Models to End-To-End Speech Recognizers

Yotaro Kubo, Shigeki Karita, Michiel Bacchiani

ICASSP 2022accepted

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 single neural network. However, as a drawback, training of end-to-end speech recognizers always requires transcribed utter…

Cited by 0 Source ↗Scholar ↗

2020

Joint Phoneme-Grapheme Model for End-To-End Speech Recognition

Yotaro Kubo, Michiel Bacchiani

ICASSP 2020accepted

This paper proposes methods to improve a commonly used end-to-end speech recognition model, Listen-Attend-Spell (LAS). The methods we propose use multi-task learning to improve generalization of the model by leveraging information from multiple labels. The focus in this paper is on multi-task models…

Cited by 0 Source ↗Scholar ↗