Residual speech signal compression: an experiment in the practical application of neural network technology
Pages 1063 - 1072
Abstract
Neural networks are a popular area of research today. However, neural network algorithms have only recently proven valuable to application problems. This paper seeks to aid in the process of transferring neural network technology from research to a development environment by describing our experience in applying this technology.
The application studied here is Speaker Identity Verification (SIV), which is the task of verifying a speaker's identity by comparing the speaker's voice pattern to a stored template.
In this paper, we describe the application of the back-propagation neural network algorithm to one aspect of the SIV problem, called Residual Compression (RC). The RC problem is to extract useful features from a part of the speech signal that was not utilized by previous SIV systems. Here, we describe a neural network architecture, pre-processing algorithm, training methodology, and empirical results for this problem. We also present a few guidelines for the use of neural networks in applied settings.
References
[1]
B AUM, E. B., AND HAUSSLER, D. What size net gives Valid Generalization? In Advances in Neural Information Processing Systems 1: {Collected papers of the IEEE Conference on Neural Information Processing Systems - Natural and Synthetic, Denver, Nov. 28-Dec. 1,1988}, D. S. Touretzky, Ed. Morgan Kaufmann, San Mateo, CA, 1989, pp. 81-90.
[2]
DENKER, J., SCHWARTZ, D., WITrNER, B., SOLLA, S., HOPFiELD, J., HOWARD, R., AND JACKEL, L. Automatic Learning, Rule Extraction, and Generalization, October 1987. Unpublished technical report.
[3]
ELMAN, J. L., AND ZIPSER, D. Learning the Hidden Structure of Speech. Tech. Rep. ICS-8701, Institute for Cognitive Science, February 1987.
[4]
FEUSTEL, T. C., AND VELIUS, G. A. Voice-Based Securry: identity Verification over Telephone Lines. In Proceedings of the IEEE Global Telecommunications Conference & Exhibition (Dallas, TX, 1989), vol. 1, IEEE, pp. 212-216.
[5]
HANSON, S. J., AND PRATI', L. Y. Comparing Biases for Minimal Network Construction with Backpropagation. In Advances in Neural Information Processing Systems 1: {Collected papers of the {EEE Conference on Neural Information Processing Systems - Natural and Synthetic, Denver, Nov. 28-Dec. 1,1988}, D. S. Touretzky, Ed. Morgan Kaufmann, San Mateo, CA, 1989, pp. 177-185.
[6]
LAPEDES, A., AND F^RBER, R. Nonlinear signal processing using Neural Networks: Prediction and system modelling. Tech. rep., Theoretical Division, Los Alarnos National Laboratory, Los Alamos, NM 87545, 1987.
[7]
MCCLELLAND, J. L., AND RUMELHART, D. E. Explorations in Parallel Distributed Processing' A Handbook of Models, Programs, and Exercises. The MIT Press, Cambridge, MA, 1988.
[8]
MCCLELLAND, J. L., RUMELHART, D. E., AND THE PDP RESEARCH GROUP. Parallel Distributed Processing, Volume 2: Psychological and Biological models. Addison-Wesley, 1986.
[9]
MORGAN, N., AND BOURLARD, H. Generalization and Parameter Estimation in Feedforward Nets: Some Experiments. In Advances in Neural Information Processing Systems 2, D. S. Touretzky, Ed. Morgan Kaufmann, San Mateo, CA, 1990.
[10]
OPPENHEIM, A. V., AND SCHAFER, R. W. Digital Signal Processing. Prentice-Hall, Englewood Cliffs, New Jersey, 1975.
[11]
RUMELHART, D. E., MECLELLAND, J. L., AND THE PDP RESEARCH GROUP, Eds. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1. MIT Press: Bradford Books, 1987.
[12]
TESAI3RO, G., AND JANSSEN$, R. Scaling relationships in back-propagation learning: dependence on predicate order. Tech. Rep. CCSR-88-1, Center for Complex Systems Research, University of Illinois at Urbana- Champaign, February 1988.
[13]
VELIUS, G. Speaker Identity Feature Combination with a Neural Net. J. Acoust. Soc. Am. Suppl. 1 84 (1988), $61.
[14]
VELIUS, G. A. Variants of Cepstrum Based Speaker Identity Verification. ICASSP 88 J (1988), 583-586.
Index Terms
- Residual speech signal compression: an experiment in the practical application of neural network technology
Recommendations
Application of BP Neural Network with Chebyshev Mapping in Image Compression
IMCCC '13: Proceedings of the 2013 Third International Conference on Instrumentation, Measurement, Computer, Communication and ControlThe traditional BP neural network has two disadvantages: long training time and easily getting into local minimum. To solve above problem, the neural network with chaotic neuron was proposed. In this paper, the Chebyshev chaotic mapping is used to ...
Neural network based pitch tracking in very noisy speech
Pitch determination is a fundamental problem in speech processing, which has been studied for decades. However, it is challenging to determinate pitch in strong noise because the harmonic structure is corrupted. In this paper, we estimate pitch using ...
Scene text recognition using residual convolutional recurrent neural network
Text is a significant tool for human communication, and text recognition in scene images becomes more and more important. In this paper, we propose a residual convolutional recurrent neural network for solving the task of scene text recognition. The ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © 1990 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 01 June 1990
Check for updates
Qualifiers
- Article
Conference
IEA/AEI-90
Sponsor:
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 846Total Downloads
- Downloads (Last 12 months)15
- Downloads (Last 6 weeks)1
Reflects downloads up to 24 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in