Enhancement of Speech Recognition System by neural network approaches of Clustering
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2013, Vol 6, Issue 1
Abstract
This paper addresses the problem of speech recognition to identify various modes of speech data. Speaker sounds are the acoustic sounds of speech. Statistical models of speech have been widely used for speech recognition under neural networks. In paper we propose and try to justify a new model in which speech co articulation the effect of phonetic context on speech sound is modeled explicitly under a statistical framework. We study speech phone recognition by recurrent neural networks and SOUL Neural Networks. A general framework for recurrent neural networks and considerations for network training are discussed in detail. SOUL NN clustering the large vocabulary that compresses huge data sets of speech. This project also different Indian languages utter by different speakers in different modes such as aggressive, happy, sad, and angry. Many alternative energy measures and training methods are proposed and implemented. A speaker independent phone recognition rate of 82% with 25% frame error rate has been achieved on the neural data base. Neural speech recognition experiments on the NTIMIT database result in a phone recognition rate of 68% correct. The research results in this thesis are competitive with the best results reported in the literature.Â
Authors and Affiliations
Anurag Upadhyay, Chitranjanjit Kaur
Keywords
Related Articles
- EP ID EP650051
- DOI 10.24297/ijct.v6i1.4456
- Views 92
- Downloads 0
E-Security Issues
With the rapid growth of e-commerce, governmental and corporate agencies are taking extra precautions when it comes to protecting information. The development of e-security as a discipline has enabled organisations to di...
AUTOMATIC ENERGY SAVING (AES) MODELTO BOOST UBIQUITOUS WIRELESS SENSOR NETWORKS (WSNs)
We deploy BT node (sensor) that offers passive and active sensing capability to save energy. BT node works in passive mode for outdoor communication and active for indoor communication. The BT node is supported with nove...
On the Error Rate and Delay Performance Analysis of OFDM based Cooperative Protocol for 802.11 Networks
We develop and analyze a distributed space-frequency block code-orthogonal frequency division multiplexing protocol for cooperative communications in 802.11 networks. Space frequency block codes (SFBC) are spread over OF...
Vehicular Traffic Monitoring Using VANET
During last few years, continuous progresses in wireless communication have open new research fields in computer network. VANET proposes communication between vehicles by wireless means has a large potential to improve s...
A novel method for secret image sharing Using nibble exchange
This paper proposes a new scheme for secret image sharing which shuffles and manipulates the nibbles (and hence the bytes) of the pixel values of the images. We have developed a new algorithm called LDRU (Left-Down-Right...