ABSTRACT
In the recent years, wavelet packet (WP) transform has been used as an important speech representation tool. WP-based acoustic features have found to be more efficient than the short-time Fourier transform (STFT)-based features to capture the information of unvoiced phoneme from continuous speech. In this paper, a new 24 sub-band equivalent rectangular bandwidth (ERB)-like wavelet filter is proposed by employing perceptual Wiener filter on each sub-band of decomposed noisy speech. Wiener filtered output is then proceeded according to the Johnston model to calculate auditory masking threshold for each wavelet decomposed sub-band. This threshold is used to design the perceptual sub-band weighting (PSW) filter. The output from each perceptually weighted sub-band is processed further to calculate acoustic front end features. This technique aims to enhance the noisy speech signal by using standard Wiener filter on psychoacoustically motivated decomposed wavelet sub-band by controlling the sub-band weighting factor. Hindi continuous digit database and TIMIT database is used to evaluate the performance of the proposed feature. Obtained results show that proposed feature is effective for noisy speech recognition compared to some recently proposed feature extraction techniques.
Acknowledgements
We are thankful to the respected reviewers and the honourable editor for providing important suggestions and constructive comments which helped us to improve the quality of the paper.
Disclosure statement
No potential conflict of interest was reported by the authors.
Additional information
Notes on contributors
Astik Biswas
Astik Biswas received his B. Tech. in 2008 from West Bengal University of Technology, Kolkata, India. He received his ME in 2010 from Birla Institute of Technology, Mesra, India, in the field of speech recognition. He worked as assistant professor in IMSEC Ghaziabad from 2010 to 2012. Currently, he is pursuing PhD at National Institute of Technology, Rourkela. His areas of interest are Speech and Signal Processing, video processing and Digital Electronics.
E-mail: [email protected]
P.K. Sahu
P.K. Sahu received B.Sc. Engineering (El and TCE) and M.Sc. Engineering (ESC) from Sambalpur University, Odisha, India. Received his PhD degree from Jadavpur University, Kolkata, India, in the year 2009. Currently, he is an associate professor in Department of Electrical Engineering at National Institute of Technology, Rourkela, Odisha, India. His research interest includes Micro and Nano Electronic Devices, VLSI, Communication Systems. He is also a life member of IEEE, IE and IETE.
E-mail: [email protected]
Anirban Bhowmick
Anirban Bhowmick received his B. Tech. in 2008 from West Bengal University of Technology, Kolkata, India. He received his ME in 2011 from Birla Institute of Technology, Mesra, India, in the field of speech recognition. Currently, he is pursuing PhD at Birla Institute of Technology, Mesra, India. His areas of interest are Speech and Signal Processing, Image Processing, Instrumentation. He is a member of IEEE.
E-mail: [email protected]
Mahesh Chandra
Mahesh Chandra received his B.Sc. from Agra University, Agra (UP), India, in 1990 and AMIE from IEI, Kolkata (WB), India, in winter 1994. He received M.Tech. from JNTU, Hyderabad, India, in 2000 and PhD from AMU, Aligarh (UP), India, in 2008. Presently, he is working as an associate professor in the Electronics and Communication Engg. Department, BIT Mesra, Ranchi (Jharkhand),India. He has published more than 115 research papers in the area of Speech, Signal and Image Processing at National/International level. His areas of interest are Speech, Signal and Image Processing.
E-mail: [email protected]