FDVQ based keyword spotter which incorporates a semi-supervised learning for primary processing
作者： Chakib Tadj , Pierre Dumouchel , Franck Poirier
DOI:
关键词:
摘要: In this paper, we present a novel hybrid keyword spotting system that combines supervised and semi-supervised competitive learning algorithms. The rst stage is S-SOM (Semi-supervised SelfOrganizing Map) module which speci cally designed for discrimination between keywords (KWs) non-keywords (NKWs). second an FDVQ (Fuzzy Dynamic Vector Quantization) consists of discriminating KWs detected by the processing. experiment on Switchboard database has show improvement about 6% accuracy comparing to our best keyword-spotter one.
isca-speech.org
etsmtl.ca参考文章(2)
T. Kohonen, The self-organizing map Proceedings of the IEEE. ,vol. 78, pp. 1464- 1480 ,(1990) , 10.1109/5.58325
J.J. Godfrey, E.C. Holliman, J. McDaniel, SWITCHBOARD: telephone speech corpus for research and development international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 517- 520 ,(1992) , 10.1109/ICASSP.1992.225858