Speech Communication - Eurospeech '91
Improved vocabulary-independent sub-word HMM modelling
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
An investigation of PLP and IMELDA acoustic representations and of their potential for combination
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Large vocabulary speech recognition using neural prediction model
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Continuous speech recognition using linked predictive neural networks
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Acoustic-phonetic transformations for improved speaker-independent isolated word recognition
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Linear discriminant analysis for improved large vocabulary continuous speech recognition
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
| Hi-index | 0.00 |
This paper shows how to additionally exploit a prediction error signal in the context-dependent Hidden Control Neural Network (HCNN-CDF) continuous speech recognition system to increase the discrimination among predictive models of the system. First, by using Linear Discriminant Analysis (LDA) we analyze the squared prediction errors of the system on a continuous speech recognition task. The results clearly show that the residual prediction error signal contains information to further support discrimination among the models of the system. LDA also determines which components of the residual prediction error signal contribute most to discrimination among the models. It is used as a tool to determine the dimensionality of the predicted error vector to be modeled. Second, using the results from discriminant analysis, we propose a new HCNN model which predicts (i.e., coniputes) the squared prediction error signal from the speech data. By using these HCNN models, we observed an increased discrimination among predictive models of the system.