Speech enhancement from noise: a regenerative approach
Speech Communication
Speech recognition in noisy environments: a survey
Speech Communication
Fast and accurate acoustic modelling with semi-continuous HMMs
Speech Communication
Noisy speech enhancement using discrete cosine transform
Speech Communication
Experimental comparison of signal subspace based noise reduction methods
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
GSVD-based optimal filtering for single and multimicrophone speech enhancement
IEEE Transactions on Signal Processing
Prewhitening for rank-deficient noise in subspace methods for noise reduction
IEEE Transactions on Signal Processing - Part I
FIR filter representations of reduced-rank noise reduction
IEEE Transactions on Signal Processing
Robust Speaker Modeling Based on Constrained Nonnegative Tensor Factorization
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Auditory sparse representation for robust speaker recognition based on tensor structure
EURASIP Journal on Audio, Speech, and Music Processing - Intelligent Audio, Speech, and Music Processing Applications
Integrated phoneme subspace method for speech feature extraction
EURASIP Journal on Audio, Speech, and Music Processing
Noise reduction algorithms in a generalized transform domain
IEEE Transactions on Audio, Speech, and Language Processing
Perceptual improvement of Wiener filtering employing a post-filter
Digital Signal Processing
MMSE estimation of log-filterbank energies for robust speech recognition
Speech Communication
Journal of Computer Science and Technology
International Journal of Speech Technology
| Hi-index | 0.00 |
The objective of this paper is threefold: (1) to provide an extensive review of signal subspace speech enhancement, (2) to derive an upper bound for the performance of these techniques, and (3) to present a comprehensive study of the potential of subspace filtering to increase the robustness of automatic speech recognisers against stationary additive noise distortions. Subspace filtering methods are based on the orthogonal decomposition of the noisy speech observation space into a signal subspace and a noise subspace. This decomposition is possible under the assumption of a low-rank model for speech, and on the availability of an estimate of the noise correlation matrix. We present an extensive overview of the available estimators, and derive a theoretical estimator to experimentally assess an upper bound to the performance that can be achieved by any subspace-based method. Automatic speech recognition (ASR) experiments with noisy data demonstrate that subspace-based speech enhancement can significantly increase the robustness of these systems in additive coloured noise environments. Optimal performance is obtained only if no explicit rank reduction of the noisy Hankel matrix is performed. Although this strategy might increase the level of the residual noise, it reduces the risk of removing essential signal information for the recogniser's back end. Finally, it is also shown that subspace filtering compares favourably to the well-known spectral subtraction technique.