Title :
Nonlinear prediction with neural nets in ADPCM
Author :
Faúndez-Zanuy, Marcos ; Vallverdú, Francesc ; Monte, Enric
Author_Institution :
Escola Univ. Politecnica de Mataro, Barcelona, Spain
Abstract :
In the last years there has been a growing interest for nonlinear speech models. Several works have been published revealing the better performance of nonlinear techniques, but little attention has been dedicated to the implementation of the nonlinear model into real applications. This work is focused on the study of the behaviour of a nonlinear predictive model based on neural nets, in a speech waveform coder. Our novel scheme obtains an improvement in SEGSNR between 1 and 2 dB for an adaptive quantization ranging from 2 to 5 bits
Keywords :
adaptive signal processing; multilayer perceptrons; neural net architecture; prediction theory; pulse code modulation; quantisation (signal); speech coding; ADPCM; SEGSNR; adaptive quantization; multilayer perceptron; neural network architecture; nonlinear model; nonlinear prediction; nonlinear speech models; performance; speech waveform coder; Bit rate; Databases; Linear predictive coding; Multilayer perceptrons; Neural networks; Neurons; Nonlinear filters; Predictive models; Quantization; Speech synthesis;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.674438
