The use of speedup techniques for a speech recogn

Authors: András Kocsor Gábor Gosztolya

Publish Date: 2008/12/02

Volume: 9, Issue: 3-4, Pages: 95-107

PDF Link

Abstract

In speech recognition not just the accuracy of an automatic speech recognition application is important but also its speed However if we want to create a realtime speech recognizer this requirement limits the time that is spent on searching for the best hypothesis which can even affect the recognition accuracy Thus the applied search method plays an important role in the speech recognition task and so does its efficiency ie how quickly it finds the uttered words To speed up this search process various ideas are available in the literature we can use search heuristics multipass search or apply a family of aggregation operators In this paper we test all these methods in turn and combine them with a set of other novel speedup ideas The test results confirm that all of these techniques are valuable using combinations of them helped make the speech recognition process over 12 times faster than the basic multistack decoding algorithm and almost 11 times faster than the Viterbi beam search method

Keywords: