Y
Yu Takahashi
Researcher at Yamaha Corporation
Publications - 102
Citations - 980
Yu Takahashi is an academic researcher from Yamaha Corporation. The author has contributed to research in topics: Blind signal separation & Non-negative matrix factorization. The author has an hindex of 16, co-authored 100 publications receiving 912 citations. Previous affiliations of Yu Takahashi include Nara Institute of Science and Technology.
Papers
More filters
Journal ArticleDOI
Blind Spatial Subtraction Array for Speech Enhancement in Noisy Environment
TL;DR: It is theoretically and experimentally pointed out that ICA is proficient in noise estimation under a non-point-source noise condition rather than in speech estimation, and a new blind spatial subtraction array (BSSA) is proposed that utilizes ICA as a noise estimator.
Journal ArticleDOI
Musical-Noise-Free Speech Enhancement Based on Optimized Iterative Spectral Subtraction
TL;DR: A theoretical analysis of the amount of musical noise in iterative spectral subtraction, and its optimization method for the least musical noise generation, and theoretically derive the optimal internal parameters that generate no musical noise.
Automatic optimization scheme of spectral subtraction based on musical noise assessment via higher-order statistics
TL;DR: IWAENC2008: the 11th International Workshop on Acoustic Echo and Noise Control, September 14-17, 2008, Seattle, Washington USA.
Journal ArticleDOI
Theoretical Analysis of Musical Noise in Generalized Spectral Subtraction Based on Higher Order Statistics
TL;DR: It is clarified that less musical noise is generated when the authors choose a lower exponent spectral domain; this implies that there is no theoretical justification for using power/amplitude spectral subtraction.
Journal ArticleDOI
Generalized independent low-rank matrix analysis using heavy-tailed distributions for blind source separation
Daichi Kitamura,Shinichi Mogami,Yoshiki Mitsui,Norihiro Takamune,Hiroshi Saruwatari,Nobutaka Ono,Yu Takahashi,Kazunobu Kondo +7 more
TL;DR: This paper introduces a heavy-tailed property by replacing the conventional Gaussian source distribution with a generalized Gaussian or Student’s t distribution in the source model estimation, and proposes two extensions of the source distribution assumed in ILRMA.