Acoustic model training for speech recognition over mobile networks Online publication date: Sun, 21-Apr-2013
by Juraj Vojtko; Juraj Kačur; Gregor Rozinaj; Ján Kőrösi
International Journal of Signal and Imaging Systems Engineering (IJSISE), Vol. 6, No. 2, 2013
Abstract: The goal of this article is to provide and present information about the training procedure SpinxTrain and its eligible modifications to get accurate and robust speech recognition in a mobile GSM environment. Some modifications are based on effective preprocessing of input data in combination with the optimal setting of the number of states per model, through the adjustment of the number of tied states or number of Gaussian mixtures. Another source of increased recognition rate is the 'optimal' setting of the speech decoder. As it is a non-linear, mathematically not well tractable task containing both real and integer values, methods of evolution strategies can be successfully used (an 18.6% improvement in WER was observed compared to the original setting). All experiments and results were obtained for the Slovak speech database Mobildat, which contains recordings of 1100 speakers. The Sphinx4 recognition system was used for evaluation of the trained model.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Signal and Imaging Systems Engineering (IJSISE):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook