no code implementations • 24 Sep 2021 • Hiroshi Seki, Takashi Nakano, Koshiro Ikeda, Shinji Hirooka, Takaaki Kawasaki, Mitsutomo Yamada, Shumpei Saito, Toshitaka Yamakawa, Shimpei Ogawa
Besides DivideMix, we used a model ensemble technique, SWA, which also focuses on the noisy label problem, to enhance the effect of the models generated by DivideMix.
no code implementations • 12 Nov 2018 • Hiroshi Seki, Takaaki Hori, Shinji Watanabe
In this paper, we propose a parallelism technique for beam search, which accelerates the search process by vectorizing multiple hypotheses to eliminate the for-loop program.
no code implementations • 27 Sep 2018 • Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
Several multi-lingual ASR systems were recently proposed based on a monolithic neural network architecture without language-dependent modules, showing that modeling of multiple languages is well within the capabilities of an end-to-end framework.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • ACL 2018 • Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
In this paper, we propose a new sequence-to-sequence framework to directly decode multiple label sequences from a single speech sequence by unifying source separation and speech recognition functions in an end-to-end manner.