Nobuyasu Itoh — accepted AI-conference papers

2020

Converting Written Language to Spoken Language with Neural Machine Translation for Language Modeling

Shintaro Ando, Masayuki Suzuki, Nobuyasu Itoh, Gakuto Kurata, Nobuaki Minematsu

ICASSP 2020accepted

When building a language model (LM) for spontaneous speech, the ideal situation is to have a large amount of spoken, in-domain training data. Having such abundant data, however, is not realistic. We address this problem by generating texts in spoken language from those in written language by using a…

Cited by 0 Source ↗Scholar ↗

2019

Improvements to N-gram Language Model Using Text Generated from Neural Language Model

Masayuki Suzuki, Nobuyasu Itoh, Tohru Nagano, Gakuto Kurata, Samuel Thomas

ICASSP 2019accepted

Although neural language models have emerged, n-gram language models are still used for many speech recognition tasks. This paper proposes four methods to improve n-gram language models using text generated from a recurrent neural network language model (RNNLM). First, we use multiple RNNLMs from di…

Cited by 0 Source ↗Scholar ↗