Fundamentals of speech recognition
Fundamentals of speech recognition
Blind Separation of Multiple Speakers in a Multipath Environment
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
Convex Kernel Underestimation of Functions with Multiple Local Minima
Computational Optimization and Applications
Identification of acoustic MIMO systems: challenges and opportunities
Signal Processing
Some extensions of score matching
Computational Statistics & Data Analysis
Projected Gradient Methods for Nonnegative Matrix Factorization
Neural Computation
Blind equalization for correlated input symbols: A Bussgang approach
IEEE Transactions on Signal Processing
Multichannel blind deconvolution of nonminimum-phase systems using filter decomposition
IEEE Transactions on Signal Processing
Blind Deconvolution of DS-CDMA Signals by Means of Decomposition in Rank- Terms
IEEE Transactions on Signal Processing
Harmonicity-Based Blind Dereverberation for Single-Channel Speech Signals
IEEE Transactions on Audio, Speech, and Language Processing
Multichannel blind deconvolution for source separation in convolutive mixtures of speech
IEEE Transactions on Audio, Speech, and Language Processing
Hi-index | 0.01 |
In order to overcome a limited performance of a conventional monaural model, this letter proposes a binaural blind dereverberation model. Its learning rule is derived using a blind least-squares measure by exploiting higher-order characteristics of output components. In order to prevent an unwanted whitening of speech signal, we adopt a semi-blind approach by employing a pre-determined whitening filter. The proposed model is evaluated using several simulated conditions and the results show better speech quality than those of the monaural model. The applicability of the model to the real environment is also shown by applying to real-recorded data. Especially, the proposed model attains much improved word error rates from 13.9+/-5.7(%) to 4.1+/-3.5(%) across 13 speakers for testing in the real speech recognition experiments.