Speech frame recognition based on less shift sensitive wavelet filter banks. Issue 4 (April 2016)

• Record Type: Journal Article
• Authors: Tohidypour, Hamid; Banitalebi-Dehkordi, Amin
• Is Part Of: Signal, image and video processing. Volume 10:Issue 4(2016)
• Page Start: 633
• Page End: 637
• Publication Date: 2016-04
• Subjects: Dual-tree complex wavelet transform (DT-CWT) -- Four-channel double-density discrete wavelet transform (FCDDDWT) -- Redundant wavelet filter bank (RWFB) -- Wavelet transform (WT) -- Speech frame recognition -- Perceptual dual-tree complex wavelet filter bank; Signal processing -- Digital techniques -- Periodicals; Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; 621.3822
• DOI: 10.1007/s11760-015-0787-z
• Languages: English
• ISSNs: 1863-1703

Abstract

Abstract The wavelet transform possesses multi-resolution property and high localization performance; hence, it can be optimized for speech recognition. In our previous work, we show that redundant wavelet filter bank parameters work better in speech recognition task, because they are much less shift sensitive than those of critically sampled discrete wavelet transform (DWT). In this paper, three types of wavelet representations are introduced, including features based on dual-tree complex wavelet transform (DT-CWT), perceptual dual-tree complex wavelet transform, and four-channel double-density discrete wavelet transform (FCDDDWT). Then, appropriate filter values for DT-CWT and FCDDDWT are proposed. The performances of the proposed wavelet representations are compared in a phoneme recognition task using special form of the time-delay neural networks. Performance evaluations confirm that dual-tree complex wavelet filter banks outperform conventional DWT in speech recognition systems. The proposed perceptual dual-tree complex wavelet filter bank results in up to approximately 9.82 % recognition rate increase, compared to the critically sampled two-channel wavelet filter bank.