Human and machine recognition as a function of SNR

Bernt Andrassy, Harald Hoege


Abstract
In-car automatic speech recognition (ASR) is usually evaluated behaviour for different levels of noise. Yet this is interesting for car manufacturers in order to predict system performances for different speeds and different car models and thus allow to design speech based applications in a better way. It therefore makes sense to split the single WER into SNR dependent WERs, where SNR stands for the signal to noise ratio, which is an appropriate measure for the noise level. In this paper a SNR measure based on the concept of the Articulation Index is developed, which allows the direct comparison with human recognition performance.
Anthology ID:
L06-1095
Volume:
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
Month:
May
Year:
2006
Address:
Genoa, Italy
Editors:
Nicoletta Calzolari, Khalid Choukri, Aldo Gangemi, Bente Maegaard, Joseph Mariani, Jan Odijk, Daniel Tapias
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2006/pdf/179_pdf.pdf
DOI:
Bibkey:
Cite (ACL):
Bernt Andrassy and Harald Hoege. 2006. Human and machine recognition as a function of SNR. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).
Cite (Informal):
Human and machine recognition as a function of SNR (Andrassy & Hoege, LREC 2006)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2006/pdf/179_pdf.pdf