Fast feature-based preclassification of segments in continuous digit recognition
- 23 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 1085-1088
- https://doi.org/10.1109/icassp.1986.1168825
Abstract
This paper describes the preclassification part of a real time speaker dependent continuous digit recognition system. The system's main characteristic is a fast feature-based word hypothesizer employing a combination of knowledge-based methods and pattern matching. This provides for a more reasonable behaviour, avoiding unintuitive errors typically found in conventional pattern matching systems. The processing can be broken up into four components: on-line segmentation according to four coarse phonetic classes, feature based matching focusing on voiced segments, word candidate generation and pruning and finally, candidate-adaptive pattern matching for decision making. The digit accuracy of the preclassifier, which includes the first 3 steps was found to be 96% in experiments using a total of 540 digit strings with an average length of 4 digits, collected from six speakers (4 male, 2 female).Keywords
This publication has 13 references indexed in Scilit:
- Speaker independent recognition of connected digitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Experiments in connected word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Speaker-independent connected digit recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- An algorithm for connected word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Hierarchical DP for word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Network-based connected digit recognition using vector quantizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The use of speech knowledge in automatic speech recognitionProceedings of the IEEE, 1985
- A level building dynamic time warping algorithm for connected word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Two-level DP-matching--A dynamic programming-based pattern matching algorithm for connected word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979
- Dynamic programming algorithm optimization for spoken word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978