Robust Speech Recognition Using Fusion Techniques and Adaptive Filtering

Al-Haddad Al-Haddad

doi:10.3844/ajassp.2009.290.295

Abstract

The study proposes an algorithm for noise cancellation by using recursive least square (RLS) and pattern recognition by using fusion method of Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). Speech signals are often corrupted with background noise and the changes in signal characteristics could be fast. These issues are especially important for robust speech recognition. Robustness is a key issue in speech recognition. The algorithm is tested on speech samples that are a part of a Malay corpus. It is shown that the fusion technique can be used to fuse the pattern recognition outputs of DTW and HMM. Furthermore refinement normalization was introduced by using weight mean vector to obtain better performance. Accuracy of 94% on pattern recognition was obtainable using fusion HMM and DTW compared to 80.5% using DTW and 90.7% using HMM separately. The accuracy of the proposed algorithm is increased further to 98% by utilization the RLS adaptive noise cancellation.

Highlights

Speech Recognition (SR) is a technique aimed at converting a speaker’s spoken utterance into a text string or other applications
Hidden markov model (HMM): Hidden Markov Model (HMM) is typically an interconnected group of states that are assumed to emit a new feature vector for each frame according to an emission probability density function associated with that state
The results obtained from the accuracy test is about 80.5% of accuracy for Dynamic Time Warping (DTW) and 90.7% for HMM and 94% for pattern recognition fusion

Summary

Introduction

Speech Recognition (SR) is a technique aimed at converting a speaker’s spoken utterance into a text string or other applications. It is quoted that the best reported word-error rates on English broadcast news and conversational telephone speech are 10 and 20%, respectively[1]. Error rates on conversational meeting speech are about 50% higher and much more under noisy conditions[2]. Recursive Least Squares (RLS) algorithm is used to improve the presence of speech in a background of noise. In many applications of noise cancellation the changes in signal characteristics could be quite fast. This requires the utilization of adaptive algorithms, which converge rapidly. From this perspective the best choice is the RLS[5]. The beginning and end of a word should be detected by the system that processes the word after noise cancellation has been done

Methods

Results

Conclusion