In this work we evaluate the performance of MMSE estimation with a media-specific FEC based on VQ replicas in comparison with MAP estimation and interleaving, both operating in a DSR system over a loss-prone packet switched network. Both schemes combine a sender-driven with a receiver-based technique and, as we show, clearly outperform the standard Aurora mitigation. However, as independent techniques, interleaving and FEC codes could be jointly applied. Although this would provide better results, a direct combination of FECs and interleaving involves a sum of the delays of both operations. In this work, we introduce a double stream-based strategy that avoids this sum of delays.
Cite as: Gómez, A.M., Peinado, A.M., Sánchez, V., Carmona, J.L., Rubio, A.J. (2006) Interleaving and MMSE estimation with VQ replicas for distributed speech recognition over lossy packet networks. Proc. Interspeech 2006, paper 1279-Tue2BuP.2, doi: 10.21437/Interspeech.2006-337
@inproceedings{gomez06b_interspeech,
author={Angel M. Gómez and Antonio M. Peinado and Victoria Sánchez and José L. Carmona and Antonio J. Rubio},
title={{Interleaving and MMSE estimation with VQ replicas for distributed speech recognition over lossy packet networks}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1279-Tue2BuP.2},
doi={10.21437/Interspeech.2006-337}
}