Learning dynamic features with neural networks for phoneme recognition
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2524-2528
Abstract
Dynamic 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.Keywords
This publication has 8 references indexed in Scilit:
- Recent advances in deep learning for speech research at Microsoft2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Large vocabulary continuous speech recognition with context-dependent DBN-HMMS2011
- A study of speech recognition for children and the elderly2002
- Use of generalized dynamic feature parameters for speech recognitionIEEE Transactions on Speech and Audio Processing, 1997
- Robust text-independent speaker identification using Gaussian mixture speaker modelsIEEE Transactions on Speech and Audio Processing, 1995
- Improved acoustic modeling for continuous speech recognition1990
- Speaker-independent phone recognition using hidden Markov modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989