Abstract
Kohonen's Self-Organizing Map (SOM) is combined with the Redundant Hash Addressing (RHA) principle. The SOM encodes the input feature vector sequence into the sequence of best-matching unit (BMU) indices and the RHA principle is then used to associate the BMU index sequence with the dictionary items. This provides a fast alternative for dynamic programming (DP) based methods for comparing and matching temporal sequences. Experiments include music retrieval and speech recognition. The separation of the classes can be improved by error-corrective learning. Comparisons to DP-based methods are presented.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Albus, J.: A new approach to manipulator control: the cerebellar model articulation controller (CMAC), J. Dynamic Systems, Measurement, and Control, Transactions of the ASME Series G 97(3) (1975), 220–228.
Kohonen, T. and Reuhkala, E.: A very fast associative method for the recognition and correction of misspelt words, based on redundant hash addressing, In: Proc. 4th International Joint Conference on Pattern Recognition (IJCPR), Kyoto, Japan, Nov. 7-10, 1978, pp. 807–809.
Kohonen, T.: Automatic formation of topological maps of patterns in a self-organizing system, In: Proc. Second Scandinavian Conference on Image Analysis (SCIA), Helsinki, Finland, 1981, pp. 214–220.
Kohonen, T., Riittinen, H., Reuhkala, E. and Haltsonen S.: On-line recognition of spoken words from a large vocabulary, In: INFORMATION SCIENCES 33 (1984), 3–30.
Kohonen, T.: Self-Organizing Maps, Springer Series in Information Sciences, Vol. 30, Springer, Heidelberg, 1995, 2nd edn 1997.
Kohonen, T.: Private communication, 1998.
Laaksonen, J.: A new reliability-based phoneme segmentation method for the neural phonetic typewriter, In: Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech), Genova, Italy, Sept. 24-26, 1991, pp. I-97–100.
Levenshtein, V.: Binary codes capable of correcting deletions, insertions, and reversals, In: Cybernetics and Control Theory 10(8) (1966), 707–710.
Reuhkala, E.: Recognition of strings of discrete symbols with special application to isolated word recognition, PhD Thesis, Helsinki University of Technology, Department of Technical Physics, Finland, 1983.
Sakoe, H. and Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition, In: IEEE Trans. on Acoustics, Speech, and Signal Processing, ASSP-26(1) (1978), 43–49.
Ventä, O.: A fast text reconstruction method for the correction of imperfect text, In: Proc. First Conference of Artificial Intelligence Applications (CAIA), Denver, Colorado, Dec. 5-7, 1984, pp. 446–452.
Ventä, O.: Associative and syntactic text correction methods for continuous speech recognition, PhD Thesis, Helsinki University of Technology, Department of Computer Science, Finland, 1990.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Somervuo, P. Redundant Hash Addressing of Feature Sequences Using the Self-Organizing Map. Neural Processing Letters 10, 25–34 (1999). https://doi.org/10.1023/A:1018606728824
Issue Date:
DOI: https://doi.org/10.1023/A:1018606728824