Fully vector-quantized neural network-based code-excited nonlinear predictive speech coding
- 1 January 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Speech and Audio Processing
- Vol. 2 (4) , 482-489
- https://doi.org/10.1109/89.326608
Abstract
This paper, we take advantage of non-linear prediction with neural networks and apply it tospeech coding. Our studies are focused on:Keywords
This publication has 16 references indexed in Scilit:
- Efficient procedures for finding the optimum innovation in stochastic codersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Real-time vector excitation coding of speech at 4800 bpsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Code-excited linear prediction(CELP): High-quality speech at very low bit ratesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Source coding and vector quantization with codebook-excited neural networksComputer Speech & Language, 1992
- On the design of connectionist vector quantizersComputer Speech & Language, 1991
- Nonlinear prediction of speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Learning in Artificial Neural Networks: A Statistical PerspectiveNeural Computation, 1989
- Pitch prediction filters in speech codingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Speech coding based upon vector quantizationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- Quantizing for minimum distortionIEEE Transactions on Information Theory, 1960