Lateral inhibition net and weighted matching algorithms for speech recognition in noise

N. B. Yoma, Fergus McInnes, Mervyn Jack

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

The authors address the problem of speech recognition with signals corrupted by white Gaussian additive noise at moderate SNR. The energy of the noise is not required. A technique based on a lateral inhibition process approximation with a multilayer neural net (the lateral inhibition net (LIN)) and neural net processing efficacy weighting in acoustic pattern matching algorithms is proposed. In the recognition procedure, the local SNR is computed by means of the autocorrelation function and is employed to estimate the efficacy of LIN in noise cancelling which is taken into account as a weight in a pattern matching algorithm. A general criterion based on weighting the frame influence in decisions according to the reliability in noise reduction is suggested, and modified versions of both HMM and DTW algorithms have been designed. To be more coherent with the conditions that define LIN, a modification in the backpropagation algorithm is also proposed
Original languageEnglish
Pages (from-to)324-330
Number of pages7
JournalIEE Proceedings on Vision, Image and Signal Processing
Issue number5
Publication statusPublished - 1996


Dive into the research topics of 'Lateral inhibition net and weighted matching algorithms for speech recognition in noise'. Together they form a unique fingerprint.

Cite this