Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
CHANNEL NOISE ROBUSTNESS FOR LOW-BITRATE REMOTE SPEECH RECOGNITION Alexis Bernard and Abeer Alwan
 

Summary: CHANNEL NOISE ROBUSTNESS FOR LOW-BITRATE REMOTE SPEECH RECOGNITION
Alexis Bernard and Abeer Alwan
Department of Electrical Engineering, University of California, Los Angeles
{abernard, alwan}@icsl.ucla.edu
ABSTRACT
In remote (or distributed) speech recognition , the recognition fea-
tures are quantized at the client, and transmitted to the server via
wireless or packet-based communication for recognition. In this
paper, we investigate the issue of robustness of remote speech
recognition applications against channel noise. The techniques pre-
sented include: 1) optimal soft decision channel decoding allowing
for error detection, 2) weighted Viterbi recognition (WVR) with
weighting coefficients based on the channel decoding reliability,
3) frame erasure concealment, and 4) WVR with weighting coef-
ficients based on the quality of the erasure concealment operation.
The techniques presented are implemented at the receiver (server),
which limit the complexity for the client, and significantly extend
the range of channel conditions for which remote recognition can
be sustained. As a case study, we illustrate that remote recognition
based on perceptual linear prediction (PLP) coefficients is able to

  

Source: Alwan, Abeer - Electrical Engineering Department, University of California at Los Angeles

 

Collections: Computer Technologies and Information Sciences