Learning dynamic features with neural networks for phoneme recognition
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractDynamic features such as delta and delta-delta of basic acoustic features have long been used in various speech applications and give satisfactory performance. The explicit physical meaning and simplicity of dynamic features clearly compound their prevalence. In this paper, we propose a new framework with neural network to learn the alternatives of traditional delta and higher order differences. Instead of embracing the interpretability and simplicity, our framework is able to learn a new transformation that simulates what differences do but is more relevant to a specific task such as phoneme recognition. We determine the best way to learn such a new transformation among several most probable alternatives. Our experiments indicate that dynamic features obtained with transformation learned this way are better than traditional differences in both frame classification and phoneme recognition. The improvement of performance is even clearer when higher-order of differences are applied. © 2014 IEEE.
All Author(s) ListZheng X., Wu Z., Meng H., Cai L.
Name of Conference2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Start Date of Conference04/05/2014
End Date of Conference09/05/2014
Place of ConferenceFlorence
Country/Region of ConferenceItaly
Detailed descriptionorganized by IEEE Signal Processing Society,
Year2014
Month1
Day1
Pages2524 - 2528
ISBN9781479928927
ISSN1520-6149
LanguagesEnglish-United Kingdom
Keywordsdeep neural network (DNN), delta, difference, higher order, neural network, phoneme recognition

Last updated on 2021-24-02 at 00:17