UPM Institutional Repository

Robust speech recognition using fusion techniques and adaptive filtering


Syed Mohamed, Syed Abdul Rahman Al-Haddad and Abdul Samad, Salina and Hussain, Aini and Ishak, Khairul Anuar and Noor, Ali O. Abid (2009) Robust speech recognition using fusion techniques and adaptive filtering. American Journal of Applied Sciences, 6 (2). pp. 290-295. ISSN 1546-9239; ESSN: 1554-3641


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.

Download File

[img] PDF
Restricted to Repository staff only

Download (118kB)

Additional Metadata

Item Type: Article
Divisions: Faculty of Engineering
DOI Number: https://doi.org/10.3844/ajassp.2009.290.295
Publisher: Science Publications
Keywords: DTW; HMM; RLS; Word bounder; Zero crossing technique
Depositing User: Fatimah Zahrah @ Aishah Amran
Date Deposited: 21 Jan 2014 06:51
Last Modified: 30 Nov 2017 08:10
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.3844/ajassp.2009.290.295
URI: http://psasir.upm.edu.my/id/eprint/17737
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item