| Paper: | SLP-L8.1 | ||
| Session: | Efficient Techniques for LVCSR | ||
| Time: | Thursday, May 18, 14:00 - 14:20 | ||
| Presentation: | Lecture | ||
| Topic: | Speech and Spoken Language Processing: Distributed Speech Recognition | ||
| Title: | AN INEXPENSIVE PACKET LOSS COMPENSATION SCHEME FOR DISTRIBUTED SPEECH RECOGNITION BASED ON SOFT-FEATURES | ||
| Authors: | Valentin Ion, Reinhold Haeb-Umbach, University of Paderborn, Germany | ||
| Abstract: | Soft-feature based speech recognition, which is an example of uncertainty decoding, has been proven to be a robust error mitigation method for distributed speech recognition over wireless channels exhibiting bit errors. In this paper we extend this concept to packet-oriented transmissions. The a posteriori probability density function of the lost feature vector, given the closest received neighbors, is computed. In the experiments, the nearest frame repetition, which is shown to be equivalent to the MAP estimate, outperforms the MMSE estimate for long bursts. Taking the variance into account at the speech recognition stage results in superior performance compared to classical schemes using point estimates. A computationally and memory efficient implementation of the proposed packet loss compensation scheme based on table lookup is presented. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012