Publications
ワークショップ (国際) A Comparative Study on Transformer vs RNN in Speech Applications
Shigeki Karita (NTT), Nanxin Chen (Johns Hopkins University), Tomoki Hayashi (Nagoya University, Human Dataware Lab. Co., Ltd.), Takaaki Hori (Mitsubishi Electric Research Laboratories,), Hirofumi Inaguma (Kyoto University), Ziyan Jiang (Johns Hopkins University), Masao Someki (Nagoya University), Nelson Enrique Yalta Soplin (Waseda University), Ryuichi Yamamoto, Xiaofei Wang (Johns Hopkins University), Shinji Watanabe (Johns Hopkins University), Takenori Yoshimura (Nagoya University, Human Dataware Lab. Co., Ltd.), Wangyou Zhang (Shanghai Jiao Tong University)
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (ASRU 2019)
2019.12.14
Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art performance in neural machine translation and other natural language processing applications. We undertook intensive studies in which we experimentally compared and analyzed Transformer and conventional recurrent neural networks (RNN) in a total of 15 ASR, one multilingual ASR, one ST, and two TTS benchmarks. Our experiments revealed various training tips and significant performance benefits obtained with Transformer for each task including the surprising superiority of Transformer in 13/15 ASR benchmarks in comparison with RNN. We are preparing to release Kaldi-style reproducible recipes using open source and publicly available datasets for all the ASR, ST, and TTS tasks for the community to succeed our exciting outcomes.
Paper :
A Comparative Study on Transformer vs RNN in Speech Applications
（外部サイト）