An experimental framework of speaker independent speech recognition system for Kashmiri language (K-ASR) system using Sphinx

Abstract

Speech to text conversion in various languages have been performed so far but no process has defined for the Kashmiri language. There has been no research done on Kashmiri speech recognition. So in this work, we describe the development as well as implementation of first CMU Sphinx-3 based speech recognizer for the Kashmiri language. Recognition of the words have been done by using hidden markov models (HMMs). Dictionary consists of 100 words, representing Kashmiri digits from one (akh) to hundred (hat). Here, we developed a speaker independent, Kashmiri - Automatic Speech Recognition (KASR) system. The System is trained and tested for 1200 words spoken by 12 male and female speakers. Maximum Accuracy of 78.33% was achieved by the K-ASR system

Authors and Affiliations

Vivek Bhardwaj

Keywords

Related Articles

Total Energy Consumption Reduction in WSN Using Mobile Sink Node

Clustering or grouping of sensor nodes is used to increase the performance of WSN as it reduces the total number of nodes taking part in data transmission. The proposed work reduces the total energy consumption of the cl...

Tracking the Accidental Victim Using Andriod Application

During disasters people face problems in communicating and informing about their location to their dear ones and will be in need of urgent help Track the victim is an application that will solve the above problem The app...

Roll of Total Quality Management & Organizational Learning

Total quality management is frequently considered to be a means for achieving competitive advantage. small businesses have several Statistical limitations when they implement quality practices. However, total quality pra...

Effect of Multi-Walled Carbon Nanotubes on Automotive and Aerospace Applications- Case Study

Generally, MWCNTs are allotropes of carbon with a cylindrical nanostructure. Nano tubes have been constructed with length-to-diameter ratio of up to 132,000,000:1, significantly larger than for any other material. These...

Seismic Analysis of Honeycomb Structure over Conventional Structure with comparative Study by using STAAD PRO

All over the world new innovations have been done by researchers so as to minimize the structural and environmental damage to the society. It has became a new trend to construct tall buildings with innovative design, Bio...

Download PDF file
  • EP ID EP245441
  • DOI -
  • Views 121
  • Downloads 0

How To Cite

Vivek Bhardwaj (2017). An experimental framework of speaker independent speech recognition system for Kashmiri language (K-ASR) system using Sphinx. International journal of Emerging Trends in Science and Technology, 4(7), 5348-5352. https://europub.co.uk/articles/-A-245441