Connectionist probability estimators in HMM arabic speech recognition using fuzzy logic

Authors:
Lilia Lazli;Mokhtar Sellami
Affiliations:
Research Laboratory in Computer Science-LRI, Department of Computer Science, Faculty of Engineer Science, Badji Mokhtar University, Annaba, Algeria;Research Laboratory in Computer Science-LRI, Department of Computer Science, Faculty of Engineer Science, Badji Mokhtar University, Annaba, Algeria
Venue:
MLDM'03 Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition
Year:
2003

Citing 7
Cited 4

A time-delay neural network architecture for isolated word recognition

Neural Networks
An adaptive fuzzy C-means algorithm for image segmentation in the presence of intensity inhomogeneities

Pattern Recognition Letters
Multi-stream adaptive evidence combination for noise robust ASR

Speech Communication - Special issue on noise robust ASR
Fuzzy Models and Algorithms for Pattern Recognition and Image Processing

Fuzzy Models and Algorithms for Pattern Recognition and Image Processing
Subband-Based Speech Recognition

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Hidden Neural Networks: A Framework for HMM/NN Hybrids

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 4 - Volume 4
AICCSA 08 The 6th IEEE/ACS international conference on computer systems and applications

AICCSA '08 Proceedings of the 2008 IEEE/ACS International Conference on Computer Systems and Applications

Improvement of the speech recognition in noisy environments using a nonparametric regression

International Journal of Parallel, Emergent and Distributed Systems
An efficient speech recognition system in adverse conditions using the nonparametric regression

Engineering Applications of Artificial Intelligence
The use of wavelet entropy in conjuction with neural network for Arabic vowels recognition

WSEAS Transactions on Signal Processing
Arabic vowels recognition based on wavelet average framing linear prediction coding and neural network

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hidden Markov Models (HMM) are nowadays the most successful modeling approach for speech recognition. However, standard HMM require the assumption that adjacent feature vectors are statistically independent and identically distributed. These assumptions can be relaxed by introducing neural networks in the HMM frame work. These neural networks particularly the Multi-Layer Perceptrons (MLP) estimate the posterior probabilities used by the HMM. We started in the frame work of this work, to investigate smoothing techniques combining MLP probabilities with those from others estimators with better properties for small values (e.g., a single Gaussian) in the framework of the learning of our MLP. The main goal of this paper is to compare the performance of speech recognition of an isolated speech Arabic databases obtained with (1) discrete HMM, (2) hybrid HMM/MLP approaches using a MLP to estimate the HMM emission probabilities and (3) hybrid FCM/HMM/MLP approaches using the Fuzzy C-Means (FCM) algorithm to segment the acoustic vectors.