Title :
A neural network algorithm for enhancing delta modulation/LPC tandem connections
Author_Institution :
ITT Defense Commun. Div., San Diego, CA, USA
Abstract :
The enhancement of coded speech which has been degraded by a tandem connection between wideband and narrowband data links, specifically a delta-modulation (CVSD 16000 b/s) to linear predictive coding (LPC) (2400 b/s) link, is discussed. Speech enhancement is achieved by developing mappings from vector quantization (VQ) codebooks trained on distorted data to VQ codebooks trained on undistorted data. Two different algorithms are adapted to the problem of generating these codebooks. These algorithms are the self-organizing feature map algorithm and learning vector quantization
Keywords :
computerised signal processing; decoding; delta modulation; digital communication systems; encoding; filtering and prediction theory; learning systems; neural nets; speech analysis and processing; telecommunications computing; 16 kbit/s; 2.4 kbit/s; DM; VQ codebooks; coded speech; delta modulation/LPC tandem connections; learning vector quantization; linear predictive coding; neural network algorithm; self-organizing feature map algorithm; speech enhancement; trained codebooks; wideband/narrowband data links connection; Books; Degradation; Delta modulation; Linear predictive coding; Narrowband; Neural networks; Signal generators; Speech coding; Speech enhancement; Vector quantization; Wideband;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Conference_Location :
Albuquerque, NM
DOI :
10.1109/ICASSP.1990.115578
