Continuous Bangla Speech Segmentation using Short-term Speech Features Extraction Approaches
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2012, Vol 3, Issue 11
Abstract
This paper presents simple and novel feature extraction approaches for segmenting continuous Bangla speech sentences into words/sub-words. These methods are based on two simple speech features, namely the time-domain features and the frequency-domain features. The time-domain features, such as short-time signal energy, short-time average zero crossing rate and the frequency-domain features, such as spectral centroid and spectral flux features are extracted in this research work. After the feature sequences are extracted, a simple dynamic thresholding criterion is applied in order to detect the word boundaries and label the entire speech sentence into a sequence of words/sub-words. All the algorithms used in this research are implemented in Matlab and the implemented automatic speech segmentation system achieved segmentation accuracy of 96%.
Authors and Affiliations
Md Mijanur Rahman , Md. Al-Amin Bhuiyan
Keywords
Related Articles
- EP ID EP135420
- DOI 10.14569/IJACSA.2012.031121
- Views 68
- Downloads 0
A Survey of IPv6 Deployment
The next-generation Internet protocol (IPv6) was designed to overcome the limitation in IPv4 by using a 128-bit address instead of a 32-bit address. In addition to solving the address the limitations, IPv6 has many impro...
Conceptual Modeling in Simulation: A Representation that Assimilates Events
Simulation is often based on some type of model of the evolved portion of the world being studied. The underlying model is a static description; the simulation itself is executed by generating events or dynamic aspects i...
Multithreaded Sliding Window Approach to Improve Exact Pattern Matching Algorithms
In this paper an efficient pattern matching ap-proach, based on a multithreading sliding window technique, is proposed to improve the efficiency of the common sequential exact pattern matching algorithms including: (i) B...
Dimensionality Reduction technique using Neural Networks – A Survey
A self-organizing map (SOM) is a classical neural network method for dimensionality reduction. It comes under the unsupervised class. SOM is a neural network that is trained using unsupervised learning to produce a...
Heuristic Evaluation of Serious Game Application for Slow-reading Students
The findings of preliminary studies found that conventional approaches were still relevant but students showed weak and moderate interest and quickly lost focus rather than technology approaches such as serious games wer...