ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Empirical comparison of two multilayer perceptron-based keyword speech recognition algorithms

_ Suhardi, Klaus Fellbaum

In this paper, an empirical comparison of two multilayer perceptron (MLP)-based techniques for key- word speech recognition (wordspotting) is described. The techniques are the predictive neural model (PNM)-based wordspotting, in which the MLP is applied as a speech pattern predictor to compute a local distance between the acoustic vector and the phone model, and the hybrid HMM/MLP-based wordspotting, where the MLP is used as a state (phone) probability estimator given acoustic vectors. The comparison was performed with the same database. According to our experiments, the hybrid HMM/MLP-based technique excels the PNM-based techniques (~6.2 %).


doi: 10.21437/Eurospeech.1997-715

Cite as: Suhardi, _., Fellbaum, K. (1997) Empirical comparison of two multilayer perceptron-based keyword speech recognition algorithms. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 2835-2838, doi: 10.21437/Eurospeech.1997-715

@inproceedings{suhardi97_eurospeech,
  author={_ Suhardi and Klaus Fellbaum},
  title={{Empirical comparison of two multilayer perceptron-based keyword speech recognition algorithms}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={2835--2838},
  doi={10.21437/Eurospeech.1997-715},
  issn={1018-4074}
}