Use of a reliability coefficient in noise cancelling by neural net and weighted matching algorithms

N B Yoma, F McInnes, M Jack

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

The problems of efficacy estimation in noise cancelling by a neural net (LIN-Lateral Inhibition Net [5]) and the use of this information in weighting matching algorithms are focused. Since the effect of noise on the speech signal is variable and the backpropagation training algorithm is essentially stochastic (most common patterns have more influence in the weights re-estimation process), it is reasonable to suppose that the LIN efficacy depends on the input and each noisy frame could be associated to a reliability coefficient that attempts to measure how reliable is the result of the neural net processing. Isolated word recognition experiments have shown that reliability weighting can result in a mean error rate reduction as high as 96, 80, 58 and 36% at SNR = 12, 6, 3 and 0dB, respectively, when the noise is white Gaussian.

Original languageEnglish
Title of host publicationICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4
EditorsHT Bunnell, W Idsardi
Place of PublicationNEW YORK
PublisherCentre for Research in Education Inclusion and Diversity
Pages2297-2300
Number of pages4
ISBN (Print)0-7803-3555-4
Publication statusPublished - 1996
Event4th International Congress on Spoken Language Processing - PHILADELPHIA
Duration: 3 Oct 19966 Oct 1996

Conference

Conference4th International Congress on Spoken Language Processing
CityPHILADELPHIA
Period3/10/966/10/96

Fingerprint

Dive into the research topics of 'Use of a reliability coefficient in noise cancelling by neural net and weighted matching algorithms'. Together they form a unique fingerprint.

Cite this