Portal de Periódicos da CAPES

Efficient MMSE-based channel error mitigation techniques. Application to distributed speech recognition over wireless channels

2005; Institute of Electrical and Electronics Engineers; Volume: 4; Issue: 1 Linguagem: Inglês

10.1109/twc.2004.840198

1558-2248

Antonio M. Peinado, Victoria Sánchez, José L. Pérez-Córdoba, Antonio J. Rubio,

Speech Recognition and Synthesis

This work addresses the mitigation of channel errors by means of efficient minimum mean-square-error (MMSE) estimation. Although powerful model-based implementations have been recently proposed, the computational burden involved can make them impractical. We propose two new approaches that maintain a good level of performance with a low computational complexity. These approaches keep the simple structure and complexity of a raw MMSE estimation, although they enhance it with additional source a priori knowledge. The proposed techniques are built on a distributed speech recognition system. Different degrees of tradeoff between recognition performance and computational complexity are obtained.