Intelligent Voice Terminal with Image Retrieval Function

Article Preview

Abstract:

In recent years, voice terminal products show the intelligentized trend. This paper presents an embedded design method of intelligent voice terminal based on pattern recognition. The design adopts Samsung S3C2410 ARM as target board, Philips Uda1341TS as audio codec, embedded Linux OS as software platform, and speech recognition is implemented through small-vocabulary voice training. To improve the effect, we use the image-retrieval technology as an auxiliary tool, which helps speech recognition module create or more accurately find a personal voice-training library. By means of image recognition, the experimental results show that the effect of speech recognition achieves an average increase of 10 percentages.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 605-607)

Pages:

2522-2525

Citation:

Online since:

December 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] H. Jiao, D. T. Lu and X. Chun: Process Automation Instrumentation. Vol. 3 (2010), p.26.

Google Scholar

[2] C. Ji, L. Qian, H. Q. Xin: Transducer and Microsystem Technologies. Vol. 6 (2010), p.33.

Google Scholar

[3] R. Yaniv and D. Burstein: IEEE Transactions on Speech and Audio Processing. Vol. 11 (2003), p.216.

Google Scholar

[4] Bahl and R. Lalit: IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 2 (1983), p.179.

Google Scholar