Search Results for author: Toru Taniguchi

Found 2 papers, 0 papers with code

An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions

no code implementations19 Apr 2019 Aswin Shanmugam Subramanian, Xiaofei Wang, Shinji Watanabe, Toru Taniguchi, Dung Tran, Yuya Fujita

This report investigates the ability of E2E ASR from standard close-talk to far-field applications by encompassing entire multichannel speech enhancement and ASR components within the S2S model.

automatic-speech-recognition Denoising +2

Speaker Selective Beamformer with Keyword Mask Estimation

no code implementations25 Oct 2018 Yusuke Kida, Dung Tran, Motoi Omachi, Toru Taniguchi, Yuya Fujita

The proposed method firstly utilizes a DNN-based mask estimator to separate the mixture signal into the keyword signal uttered by the target speaker and the remaining background speech.

automatic-speech-recognition Speech Recognition

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