Simple Search:

Robust digit recognition with dynamic time warping and recursive least squares


Citation

Al-Haddad, Syed Abdul Rahman and Ishak, Khairul Anuar and Abdul Samad, Salina and Abid, Ali O. and Hussain, Noor Aini (2008) Robust digit recognition with dynamic time warping and recursive least squares. In: International Symposium on Information Technology, 26-29 Aug. 2008, Kuala Lumpur, Malaysia. (pp. 1-8).

Abstract / Synopsis

Robustness is a key issue in speech recognition. This paper proposes a speech recognition algorithm for Malay digits from 0 to 9. This paper also proposes an algorithm for noise cancellation by using recursive least squares (RLS). This system consists of speech processing inclusive of digit margin and recognition which uses zero crossing and energy calculations. Mel-Frequency Cepstral Coefficient (MFCC) vectors are used to provide an estimate of the vocal tract filter. Meanwhile dynamic time warping (DTW) is used to detect the nearest recorded voice with appropriate global constraint. The global constraint is used to set a valid search region because the variation of the speech rate of the speaker is considered to be limited in a reasonable range, which means that it can prune the unreasonable search space. The algorithm is tested on speech samples that are recorded as a part of a Malay corpus. The results show that the algorithm can recognize almost 80.5% of the Malay digits for all recorded words. By adding RLS noise canceller in the preprocessing stage it increases the accuracy to 92.3%.


Download File

Full text not available from this repository.

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Engineering
DOI Number: https://doi.org/10.1109/ITSIM.2008.4631680
Keywords: Robustness; Speech recognition; Algorithm; Digit margin; Recognition; Vocal tract; Filter; Time warping; Voice
Depositing User: Fatimah Zahrah @ Aishah Amran
Date Deposited: 06 Jan 2014 17:23
Last Modified: 03 Feb 2016 15:05
URI: http://psasir.upm.edu.my/id/eprint/16587
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item