Publication Details
Title: Experiments with Noise Reduction Neural Networks for Robust Speech Recognition
Author: M. Trompf
Group: ICSI Technical Reports
Date: May 1992
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1992/tr-92-035.pdf
Overview:
Speech recognition systems with small and medium vocabularies are used as natural human interface in a variety of real world applications. Though they work well in a laboratory environment, a significant loss in recognition performance can be observed in the presence of background noise. In order to make such a system more robust, the development of a neural network based noise reduction module is described in this paper. Based on function approximation techniques using multilayer feedforward networks (Hornik et al. 1990), this approach offers inherent nonlinear capabilities as well as easy training from pairs of corresponding noisy and noise-free signal segments. For the development of a robust nonadaptive system, information about the characteristics of the noise and speech components of the input signal and its past and future context is taken into account. Evaluation of each step is done by a word recognition task and includes experiments with changing signal parameters and sources to test the robustness of this neural network based approach.
Bibliographic Information:
ICSI Technical Report TR-92-035
Bibliographic Reference:
M. Trompf. Experiments with Noise Reduction Neural Networks for Robust Speech Recognition. ICSI Technical Report TR-92-035, May 1992
Author: M. Trompf
Group: ICSI Technical Reports
Date: May 1992
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1992/tr-92-035.pdf
Overview:
Speech recognition systems with small and medium vocabularies are used as natural human interface in a variety of real world applications. Though they work well in a laboratory environment, a significant loss in recognition performance can be observed in the presence of background noise. In order to make such a system more robust, the development of a neural network based noise reduction module is described in this paper. Based on function approximation techniques using multilayer feedforward networks (Hornik et al. 1990), this approach offers inherent nonlinear capabilities as well as easy training from pairs of corresponding noisy and noise-free signal segments. For the development of a robust nonadaptive system, information about the characteristics of the noise and speech components of the input signal and its past and future context is taken into account. Evaluation of each step is done by a word recognition task and includes experiments with changing signal parameters and sources to test the robustness of this neural network based approach.
Bibliographic Information:
ICSI Technical Report TR-92-035
Bibliographic Reference:
M. Trompf. Experiments with Noise Reduction Neural Networks for Robust Speech Recognition. ICSI Technical Report TR-92-035, May 1992