The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Speech Feature Evaluation for Bangla Automatic Speech Recognition
|
|
Author(s): Mohammed Rokibul Alam Kotwal (United International University, Bangladesh), Foyzul Hassan (United International University, Bangladesh)and Mohammad Nurul Huda (United International University, Bangladesh)
Copyright: 2013
Pages: 40
Source title:
Technical Challenges and Design Issues in Bangla Language Processing
Source Author(s)/Editor(s): M. A. Karim (Old Dominion University, USA), M. Kaykobad (Bangladesh University of Engineering & Technology, Bangladesh)and M. Murshed (Monash University, Australia)
DOI: 10.4018/978-1-4666-3970-6.ch009
Purchase
|
Abstract
This chapter presents Bangla (widely known as Bengali) Automatic Speech Recognition (ASR) techniques by evaluating the different speech features, such as Mel Frequency Cepstral Coefficients (MFCCs), Local Features (LFs), phoneme probabilities extracted by time delay artificial neural networks of different architectures. Moreover, canonicalization of speech features is also performed for Gender-Independent (GI) ASR. In the canonicalization process, the authors have designed three classifiers by male, female, and GI speakers, and extracted the output probabilities from these classifiers for measuring the maximum. The maximization of output probabilities for each speech file provides higher correctness and accuracies for GI speech recognition. Besides, dynamic parameters (velocity and acceleration coefficients) are also used in the experiments for obtaining higher accuracy in phoneme recognition. From the experiments, it is also shown that dynamic parameters with hybrid features also increase the phoneme recognition performance in a certain extent. These parameters not only increase the accuracy of the ASR system, but also reduce the computation complexity of Hidden Markov Model (HMM)-based classifiers with fewer mixture components.
Related Content
|
Reinaldo Padilha França, Ana Carolina Borges Monteiro, Rangel Arthur, Yuzo Iano.
© 2021.
21 pages.
|
|
Abdul Kader Saiod, Darelle van Greunen.
© 2021.
28 pages.
|
|
Aswini R., Padmapriya N..
© 2021.
22 pages.
|
|
Zubeida Khan, C. Maria Keet.
© 2021.
21 pages.
|
|
Neha Gupta, Rashmi Agrawal.
© 2021.
20 pages.
|
|
Kamalendu Pal.
© 2021.
14 pages.
|
|
Joy Nkechinyere Olawuyi, Bernard Ijesunor Akhigbe, Babajide Samuel Afolabi, Attoh Okine.
© 2021.
19 pages.
|
|
|