Abstract
in this paper, we propose a novel architecture of wavelet network called Multi-input Multi-output Wavelet Network MIMOWN as a generalization of the old architecture of wavelet network. This newel prototype was applied to speech recognition application especially to model acoustic unit of speech. The originality of our work is the proposal of MIMOWN to model acoustic unit of speech. This approach was proposed to overcome limitation of old wavelet network model. The use of the multi-input multi-output architecture will allows training wavelet network on various examples of acoustic units.
Highlights
The development of robust systems for speech recognition is one of the main issues of language processing
To solve some problems of modelling and recognition of speech, we suggest a new method based on wavelet networks [21] that exploit the intrinsic properties of the speech signal, while the statistical models are concerned with statistical properties of the speech signal [2]
Training algorithms for wavelet network require a smaller number of iterations when compared with neural network
Summary
The development of robust systems for speech recognition is one of the main issues of language processing. The proposed algorithm car train a MIMOWN on original vector and not on unitary random vector as in [23][24][25] Thinks to those models, the training system can model a variety of occurrences of a single entity by a single acoustic wavelet network [22]. The newel approach can be seen as a superposition of finite number of single-input single-output wavelet network Those prototypes are used to model acoustic unit of speech to be used on speech recognition system. These new models are similar to multilayer neural network for the structure and the training approach. The finale part illustrates the results that crown our approach
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
