News
Paper accepted at ICASSP2022
January 24, 2022
Our paper has been accepted at IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2022)(external link).
Robust adaptive noise canceller algorithm with SNR-based stepsize control and noise-path gain compensation
Akihiko Sugiyama
Non-Autoregressive end-to-end automatic speech recognition incorporating downstream natural language processing
Motoi Omachi, Yuya Fujita, Tianzi Wang (Johns Hopkins University), Shinji Watanabe (Carnegie Mellon University)
An exploration of HUBERT with large number of cluster units and model assessment using Bayesian information criterion
Takashi Maekaku, Yuya Fujita, Xuankai Chang (Carnegie Mellon University), Shinji Watanabe (Carnegie Mellon University)