• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.753-756
• /
• 2000

In this paper we present and compare two different spatio-temporal decorrelation learning algorithms for updating the weights of a linear feedforward network with FIR synapses (MIMO FIR filter). Both standard gradient and the natural gradient are employed to derive the spatio-temporal decorrelation algorithms. These two algorithms are applied to multichannel blind deconvolution task and their performance is compared. The rigorous derivation of algorithms and computer simulation results are presented.

• ETRI Journal
• /
• v.29 no.3
• /
• pp.300-304
• /
• 2007

This paper proposes a new data-driven method for high-pass approaches, which suppresses slow-varying noise components. Conventional high-pass approaches are based on the idea of decorrelating the feature vector sequence, and are trying for adaptability to various conditions. The proposed method is based on temporal local decorrelation using the information-maximization theory for each utterance. This is performed on an utterance-by-utterance basis, which provides an adaptive channel normalization filter for each condition. The performance of the proposed method is evaluated by isolated-word recognition experiments with channel distortion. Experimental results show that the proposed method yields outstanding improvement for channel-distorted speech recognition.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.143-151
• /
• 2012

A new data-driven method for the design of a blind modulation frequency filter that suppresses the slow-varying noise components is proposed. The proposed method is based on the temporal local decorrelation of the feature vector sequence, and is done on an utterance-by-utterance basis. Although the conventional modulation frequency filtering approaches the same form regardless of the task and environment conditions, the proposed method can provide an adaptive modulation frequency filter that outperforms conventional methods for each utterance. In addition, the method ultimately performs channel normalization in a feature domain with applications to log-spectral parameters. The performance was evaluated by speaker-independent isolated-word recognition experiments under additive noise environments. The proposed method achieved outstanding improvement for speech recognition in environments with significant noise and was also effective in a range of feature representations.

• Journal of Communications and Networks
• /
• v.6 no.1
• /
• pp.26-34
• /
• 2004

A blind interference canceller in the presence of subchipspaced multipath channels for direct-sequence code division multiple access (DS-CDMA) down-link system is considered. This technique is based on combining the existing blind interference canceller with a technique that involves assigning subchip-tap spacing to the Rake receiver. The proposed receiver minimizes the receiver’s output energy subject to a constraint in order to mitigate the multiple access interference (MAI) along each multipath component, and then suboptimally combining all the multipath components. Moreover, it is able to mitigate the mismatch problem when subchip-spaced multipath components arrive at the blind interference canceller. It is known that optimal combining techniques perform a decorrelation operation before combining, which requires both knowledge and computational complexity. In the following, we have adopted a simpler but suboptimum approach in the combining of the suppressed signals at the output of our proposed receiver. Computer simulation results verify the effectiveness of the proposed receiver to handle subchip-spaced multipath components and still suppresses MAI significantly.