serajul

Username: serajul

Participant details

	Network Member	Serajul Haque
	Organisation/Institution	University of Western Australia
	Department/Centre	Centre for Intelligent Information Processing (CIIPS)
	Lab	Signal and Information Processing
	Website
	Research area	Speech Science
	Research keywords	Speech Science

Research Interests

Principal research interest include speech information processing and recognition, and auditory and perceptual processing. Research includes application of features of auditory perception for automatic speech recognition (ASR) and man machine dialog system . An auditory model based on zero-crossings with peak amplitudes (ZCPA) was used as a front-end for automatic speech recognition (ASR) with the perceptual property of adaptation and two-tone suppression as determined by psychoacoustic observations. The model performance was evaluated on the isolated digits (TIDIGITS) database using continuous density HMM recognizer in additive noise environment. Experimental results indicate that the ASR performance of the ZCPA may be improved with adaptation over the static baseline performance in white Gaussian and factory noise. The perceptual front-end was also evaluated with dynamic (delta and delta-delta) features.It was observed that adaptation with dynamic features performed better in factory, babble and car noise over a wide range of SNR values. It is shown that for a zero-crossing based temporal speech processing, a high frequency enhancement technique such as adaptation works better in Gaussian noise, while a low frequency enhancement technique like two tone suppression works better in non Gaussian noise environment. Other perceptual features which has been applied for automatic speech recognition include frequency dependent asymmetric compression. Future work include auditory-motivated feature extraction methods based on cochlear nucleus processing for automatic speech recognition.

Representative Publications

www.ieee.org, S.Haque, Roberto Togeneri, Anthony Zaknich,"A temporal auditory model with adaptation for automatic speech recognition"," ICASSP 2007

www.assta.org, S.Haque, Roberto Togneri, Anthony Zaknich,"Zero-crossings with adaptation for automatic speech recognition", 11th International Conference on Speech Science and Technology (ASSTA 2006)