Title
Investigations into the relationship between measurable speech quality and speech recognition rate for telephony speech
Abstract
In this paper, an investigation to establish a possible relationship between the performance of a telephony speech recognition system and the method for objective speech quality assessment described in ITU-T Recommendation P.862, known as Perceptual Evaluation of Speech Quality (PESQ), is presented. Experiments using various additive background noises, and at different separations between the microphone and the sound-source have been conducted to establish such a relationship. The preliminary results suggest that telephony speech recognition rates can be mapped to the mean opinion score (MOS) obtained by PESQ using a relatively simple polynomial relationship. This indicates that the PESQ MOS can act as a reliable predictor for the achievable speech recognition rates for telephony-based speech recognition systems.
Year
DOI
Venue
2004
10.1109/ICASSP.2004.1326123
ICASSP (1)
Keywords
Field
DocType
telephony speech,achievable speech recognition rates,speech recognition,mean opinion score,microphone-sound-source separation,telephony,additive background noises,measurable speech quality,pesq mos,perceptual evaluation of speech quality,performance,itu-t recommendation p.862,background noise,degradation,automatic speech recognition,acoustic noise
Computer science,Voice activity detection,PSQM,Speech recognition,Mean opinion score,Telephony,POLQA,PESQ,Acoustic model,Intelligibility (communication)
Conference
Volume
ISSN
ISBN
1
1520-6149
0-7803-8484-9
Citations 
PageRank 
References 
8
0.81
4
Authors
3
Name
Order
Citations
PageRank
Hanwu Sun19814.15
Louis Shue220620.75
Jianfeng Chen317717.78