Shinji Watanabe
Johns Hopkins University
543 Papers
2.9K Citations
Shinji Watanabe is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 53, co-authored 383 publications. Previous affiliations of Shinji Watanabe include Mitsubishi Electric Research Laboratories & Mitsubishi.
Chat about Author
Papers
Multi-Modal Data Augmentation for End-to-end ASR.
Adithya Renduchintala,Shuoyang Ding,Matthew Wiesner,Shinji Watanabe +3 more
- 01 Jan 2018
TL;DR: In this article, a multi-modal data augmentation network (MMDA) is proposed to combine acoustic and symbolic input for ASR, which enables seamless mixing of large text datasets with significantly smaller transcribed speech corpora during training.
58
•Posted Content
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit.
Yiming Wang,Tongfei Chen,Hainan Xu,Shuoyang Ding,Hang Lv,Yiwen Shao,Nanyun Peng,Lei Xie,Shinji Watanabe,Sanjeev Khudanpur +9 more
TL;DR: Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4-11x faster for decoding than similar systems (e.g. ESPNET).
56
Semi-supervised End-to-end Speech Recognition Using Text-to-speech and Autoencoders
Shigeki Karita,Shinji Watanabe,Tomoharu Iwata,Marc Delcroix,Atsunori Ogawa,Tomohiro Nakatani +5 more
- 12 May 2019
TL;DR: Speech and text autoencoders that share encoders and decoders with an automatic speech recognition (ASR) model are introduced to improve ASR performance with large speech only and text only training datasets.
55
Transfer Learning of Language-independent End-to-end ASR with Language Model Fusion
Hirofumi Inaguma,Jaejin Cho,Murali Karthick Baskar,Tatsuya Kawahara,Shinji Watanabe +4 more
- 12 May 2019
TL;DR: In this article, an external language model (LM) is integrated into the decoder network of the attention-based S2S model in the whole adaptation stage, to effectively incorporate linguistic context of the target language.
54
Structure discovery of deep neural network based on evolutionary algorithms
Takahiro Shinozaki,Shinji Watanabe +1 more
- 06 Aug 2015
TL;DR: The proposed approach parametrizes the DNN structure by a directed acyclic graph, and the Dnn structure is represented by a simple binary vector that efficiently optimize the performance jointly with respect to the above binary vector and the other tuning parameters.