Paper Info
Title
Packet Loss Concealment Based On Vq Replicas And Mmse Estimation Applied To Distributed Speech Recognition
Abstract
This paper proposes a new packet loss concealment technique based on the inclusion in each packet of a few FEC bits, representing data replicas, combined with a minimum mean square error estimation (MMSE). This technique is developed for an Aurora-2 distributed speech recognition system working over an IP network. In addition to the data representing the transmitted speech frames, each packet includes some FEC bits representing a strongly VQ-quantized version (replicas) of previous and subsequent frames. When a loss burst occurs, the lost frames can be reconstructed from the VQ replicas. In order to mitigate the degradation introduced by the coarse VQ quantization of the replicas, a model-based MMSE estimation is applied. The experimental results show that, under a strongly degraded channel. it is possible to obtain up to 83.31% of word accuracy with only 4 FEC bits or 88.47% with 8 FEC bits per packet, when the Aurora mitigation algorithm only obtains 76.98%.
Year
DOI
Venue
2005
10.1109/ICASSP.2005.1415117
2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING
Keywords
Field
DocType
ip network,minimum mean square error,forward error correction,degradation,speech recognition,quantization,hidden markov models
Packet loss concealment,Forward error correction,Computer science,Network packet,Minimum mean square error,Internet protocol suite,Communication channel,Speech recognition,Quantization (signal processing),Hidden Markov model
Conference
ISSN
Citations 
PageRank 
1520-6149
8
0.69
References 
Authors
4
5
Name
Order
Citations
PageRank
Antonio M. Peinado137641.97
Angel M. Gomez26714.54
Victoria E. Sánchez310014.72
José L. Pérez-Córdoba417515.79
Antonio J. Rubio546636.14