Y
Yosuke Izumi
Researcher at University of Tokyo
Publications - 4
Citations - 112
Yosuke Izumi is an academic researcher from University of Tokyo. The author has contributed to research in topics: Background noise & Blind signal separation. The author has an hindex of 3, co-authored 4 publications receiving 112 citations.
Papers
More filters
Proceedings ArticleDOI
Sparseness-Based 2CH BSS using the EM Algorithm in Reverberant Environment
TL;DR: A new approach to sparseness-based BSS based on the EM algorithm, which iteratively estimates the DOA and the time-frequency mask for each source through the EM algorithms under the sparsness assumption is proposed.
Patent
Sound source separation and localization method
TL;DR: In this article, a new algorithm in which expectation maximization (EM) algorithm is applied for a blind sound source separation (BSS) problem, is proposed, in which a sound source direction which gives a maximum likelihood and a contribution rate of each sound source to each time frequency component, are estimated by the EM algorithm.
Proceedings ArticleDOI
A sparse component model of source signals and its application to blind source separation
TL;DR: A new method of blind source separation (BSS) for music signals is proposed that is a combination of the sparseness-based model of source signals and the factorized basis model in nonnegative matrix factorization (NMF).
Proceedings ArticleDOI
Stereo-input Speech Recognition using Sparseness-based Time-frequency Masking in a Reverberant Environment
Yosuke Izumi,Kenta Nishiki,Kenta Nishiki,Shinji Watanabe,Takuya Nishimoto,Nobutaka Ono,Shigeki Sagayama +6 more
TL;DR: Noise robust automatic speech recognition is presented using sparseness-based underdetermined blind source separation (BSS) technique and it is revealed that soft mask is better than binary mask in terms of recognition performance and cepstral mean normalization (CMN) reduces the distortion, especially for that caused by soft mask.