| Paper: | SLP-L8.4 | ||
| Session: | Efficient Techniques for LVCSR | ||
| Time: | Thursday, May 18, 15:00 - 15:20 | ||
| Presentation: | Lecture | ||
| Topic: | Speech and Spoken Language Processing: Resource constrained ASR for portable/mobile devices | ||
| Title: | Gaussian Selection with Non-Overlapping Clusters for ASR in Embedded Devices | ||
| Authors: | Jussi Leppänen, Imre Kiss, Nokia Research Center, Finland | ||
| Abstract: | In this paper we propose a memory efficient version of the Gaussian Selection (GS) scheme, which is used for speeding up the likelihood calculations of an ASR system. The memory savings are achieved by using non-overlapping (disjoint) clusters instead of the overlapping clusters normally used in GS. As we will show, the new scheme achieves 66% computational savings with a relative increase in word error rate (WER) of 4%. We will also show, that combining the new GS scheme with frame rate reduction and feature masking provides further savings in computation. 75% (4% increase in WER) and 68% (3.5% increase in WER) savings were obtained by adding frame rate reduction and feature masking, respectively. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012