Connected digit recognition using a level-building DTW algorithm
- 1 June 1981
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Acoustics, Speech, and Signal Processing
- Vol. 29 (3) , 351-363
- https://doi.org/10.1109/tassp.1981.1163586
Abstract
In this paper we present a novel method for recognizing a string of connected digits based upon the use of a recently proposed level-building dynamic time warping (DTW) algorithm. The recognition system attempts to build up the string, level-by-level (i.e., digit-by-digit), by comparing portions of the test string to isolated digit reference patterns. A backtracking procedure is used to find the "best" string (i.e., minimum accumulated distance) as well as a set of reasonable alternative candidates. The system was tested on a number of talkers speaking variable length digit strings (from two to five digits) over dialed up telephone lines. String error rates of 4.8 percent and 4.6 percent were obtained for speaker-trained and speaker-independent systems. Word error rates of 0.7 percent (for speaker-trained tests) and 0.9 percent (for speaker-independant tests) were obtained. The digit reference templates were obtained from autocorrelation averaging of a pair of isolated word templates for each digit of the speaker-trained system, and from a clustering analysis of isolated words for the speaker-independent system.Keywords
This publication has 15 references indexed in Scilit:
- A level building dynamic time warping algorithm for connected word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- A simplified, robust training procedure for speaker trained, isolated word recognition systemsThe Journal of the Acoustical Society of America, 1980
- Application of dynamic time warping to connected digit recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- Two-level DP-matching--A dynamic programming-based pattern matching algorithm for connected word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979
- Talker-independent speech recognition in commercial environmentsThe Journal of the Acoustical Society of America, 1979
- Interactive clustering techniques for selecting speaker-independent reference templates for isolated word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979
- Considerations in dynamic time warping algorithms for discrete word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978
- A statical decision approach to the recognition of connected digitsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976
- Evaluation of an automatic word recognition system over dialed-up telephone linesThe Journal of the Acoustical Society of America, 1976
- Minimum prediction residual principle applied to speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975