Feature selection for improved bandwidth extension of speech signals
作者： P. Jax , P. Vary
DOI: 10.1109/ICASSP.2004.1326081
关键词:
摘要: The aim of artificial bandwidth extension (BWE) is to convert speech signals with "standard telephone" quality (frequencies up 3.4 kHz) into 7 kHz wideband speech. principal key high BWE the estimation spectral envelope In general, this based on a number features that are extracted from narrowband input signal. We investigate potential and evaluate their suitability for application. each feature quantified in terms statistical measures mutual information separability. It turns out best results obtained by using large "super-vector" (/spl rarr/ information) which subsequently reduced dimension linear discriminant analysis separability). This solution also helps reduce computational complexity envelope.
sci-hub.se 参考文章(9)
J.W. Paulus, Variable Bitrate Wideband Speech Coding Using Perceptually Motivated Thresholds ieee workshop on speech coding for telecommunications. pp. 35- 36 ,(1995) , 10.1109/SCFT.1995.658114
Peter Jax, Peter Vary, On artificial bandwidth extension of telephone speech Signal Processing. ,vol. 83, pp. 1707- 1719 ,(2003) , 10.1016/S0165-1684(03)00082-3
Thomas M. Cover, Joy A. Thomas, Elements of information theory ,(1991)
P. Hedelin, J. Skoglund, Vector quantization based on Gaussian mixture models IEEE Transactions on Speech and Audio Processing. ,vol. 8, pp. 385- 401 ,(2000) , 10.1109/89.848220
Mattias Nilsson, Harald Gustaftson, Soren Vang Andersen, W. Bastiaan Kleijn, Gaussian mixture model based mutual information estimation between frequency bands in speech international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 525- 528 ,(2002) , 10.1109/ICASSP.2002.5743770
Peter Jax, Peter Vary, An upper bound on the quality of artificial bandwidth extension of narrowband speech signals international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 237- 240 ,(2002) , 10.1109/ICASSP.2002.5743698
Keinosuke Fukunaga, Introduction to Statistical Pattern Recognition ,(1972)
Yan Ming Cheng, D. O'Shaughnessy, P. Mermelstein, Statistical recovery of wideband speech from narrowband speech IEEE Transactions on Speech and Audio Processing. ,vol. 2, pp. 544- 548 ,(1994) , 10.1109/89.326637
Jax, Vary, An upper bound on the quality of artificial bandwidth extension of narrowband speech signals international conference on acoustics, speech, and signal processing. ,vol. 1, ,(2002) , 10.1109/ICASSP.2002.1005720