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 language | English |
---|---|
Title of host publication | ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 |
Editors | HT Bunnell, W Idsardi |
Place of Publication | NEW YORK |
Publisher | Centre for Research in Education Inclusion and Diversity |
Pages | 2297-2300 |
Number of pages | 4 |
ISBN (Print) | 0-7803-3555-4 |
Publication status | Published - 1996 |
Event | 4th International Congress on Spoken Language Processing - PHILADELPHIA Duration: 3 Oct 1996 → 6 Oct 1996 |
Conference
Conference | 4th International Congress on Spoken Language Processing |
---|---|
City | PHILADELPHIA |
Period | 3/10/96 → 6/10/96 |