Search Results for author: Shigeki Karita

Found 7 papers, 2 papers with code

A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition

no code implementations9 Jun 2021 Shigeki Karita, Yotaro Kubo, Michiel Adriaan Unico Bacchiani, Llion Jones

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 is able to model character sequences directly.

automatic-speech-recognition Data Augmentation +2

Unsupervised Learning of Disentangled Speech Content and Style Representation

no code implementations24 Oct 2020 Andros Tjandra, Ruoming Pang, Yu Zhang, Shigeki Karita

We present an approach for unsupervised learning of speech representation disentangling contents and styles.

Fine-tuning Speaker Recognition

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