title   
  

Görsel-işitsel tandem sınıflandırıcılar ve birleşimleri ile konuşma tanıma başarısını arttırma (Improving speech recognition with audio-visual tandem classifiers and their fusions)

Topkaya, İbrahim Saygın and Şen, Mehmet Umut and Yılmaz, Mustafa Berkay and Erdoğan, Hakan (2011) Görsel-işitsel tandem sınıflandırıcılar ve birleşimleri ile konuşma tanıma başarısını arttırma (Improving speech recognition with audio-visual tandem classifiers and their fusions). In: IEEE 19th Conference on Signal Processing and Communications Applications (SIU 2011), Kemer, Antalya

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/SIU.2011.5929673

Abstract

“Tandem approach” is a method used in speech recognition to increase performance by using classifier posterior probabilities as observations in a hidden Markov model. In this work we study the effect of using multiple visual tandem features to improve audio-visual recognition accuracy. In addition, we investigate methods to combine outputs of several audio and visual tandem classifiers with a classifier fusion system to generate outputs using learned weights. Experiments show that both approaches help to improve audio-visual speech recognition with respect to regular audio-visual speech recognition especially in noisy environments.

Item Type:Papers in Conference Proceedings
Uncontrolled Keywords:audio-visual tandem classifiers , audiovisual recognition accuracy , hidden Markov model , multiple visual tandem features , posterior probabilities , speech recognition , tandem approach
Subjects:UNSPECIFIED
ID Code:18535
Deposited By:Hakan Erdoğan
Deposited On:24 Dec 2011 22:15
Last Modified:24 Dec 2011 22:15

Repository Staff Only: item control page