Speaking rate control based on time-scale modification and its effects on the performance of speech recognition Online publication date: Tue, 17-Jun-2014
by Jin Ah Kang; Seung Ho Choi
International Journal of Engineering Systems Modelling and Simulation (IJESMS), Vol. 6, No. 1/2, 2014
Abstract: In this paper, we describe the influence of speaking rate on speech recognition. Speaking rate of input speech is controlled by applying a time-scale modification (TSM) algorithm and speaking rate normalisation is achieved by selecting a scale factor of TSM. The scale factor selection for training and testing of a speech recognition system is performed based on a maximum likelihood criterion during HMM decoding. From the experimental results, we showed that optimal selection of a TSM scale factor in speaking rate normalisation can reduce WER by 47.6% compared to the baseline.
Online publication date: Tue, 17-Jun-2014
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 Engineering Systems Modelling and Simulation (IJESMS):
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 firstname.lastname@example.org