Title :
A novel implementation of the spectral shaping approach for artificial bandwidth extension
Author :
Pham, Thuy V. ; Schaefer, Friedrich ; Kubin, Gernot
Author_Institution :
Dept. of Electron. & Telecommun. Eng., Danang Univ. of Technol., Danang, Vietnam
Abstract :
We present a novel implementation of the spectral shaping approach for artificial bandwidth extension (ABE). The spectral envelope in the missing band is adaptively tuned by a set of controlled subband powers predicted by a feedforward neural network (FFNN) in conjunction with the use of spline interpolation. There are three main aspects to this study: First, objective quality measures are exploited to select a proper feature vector, to choose relevant critical subbands and to train the network effectively. Second, the extensions toward high and low frequencies are evaluated explicitly. Third, a large assortment of empirical results on speech quality and speech intelligibility is provided. The obtained results indicate a significant improvement of the extended speech w.r.t. the narrowband speech.
Keywords :
feedforward neural nets; interpolation; speech processing; splines (mathematics); artificial bandwidth extension; controlled subband power; feature vector; feedforward neural network; narrowband speech; objective quality measure; spectral envelope; spectral shaping; speech intelligibility; speech quality; spline interpolation; artificial bandwidth extension; neural network; spectral shaping;
Conference_Titel :
Communications and Electronics (ICCE), 2010 Third International Conference on
Conference_Location :
Nha Trang
Print_ISBN :
978-1-4244-7055-6
DOI :
10.1109/ICCE.2010.5670721