Voiced-unvoiced-silence detection using the Itakura LPC distance measure
Authors:
- L. RabinerLRL. Rabiner
- M. SamburMSM. Sambur
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 323-326
Abstract
Absfraa One of the most difficult problems in speech analysis is reliable discrimination among silence, unvoiced speech, and voiced speech which has been transmitted over a telephone line. Although several methods have been proposed for making this 3-level deci- sion, these schemes have met with only modest success. In this paper a novel approach to the voiced-unvoiced-silence detection problem is proposed in which a spectral characterization of each of the 3 classes of signal is obtained during a training session, and an LPC distance metric and an energy distance are nonlinearly com- bined to make the final discrimination. This algorithm has been tested over conventional switched telephone lines, across a variety of speakers, and has been found to have an error rate of about 5%, with the majority of the errors (about 2/3) occurring at the boun- daries between signal classes. The algorithm is currently being used in a speaker independent word recognition system.Keywords
This publication has 12 references indexed in Scilit:
- A speaker-independent, syntax-directed, connected word recognition system based on hidden Markov models and level buildingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985
- Evaluation of a Statistical Approach to Voiced-Unvoiced-Silence Analysis for Telephone-Quality SpeechBell System Technical Journal, 1977
- Speech encryption by manipulations of LPC parametersThe Journal of the Acoustical Society of America, 1976
- A pattern recognition approach to voiced-unvoiced-silence classification with applications to speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976
- Real-time digital hardware pitch detectorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976
- Applications of a nonlinear smoothing algorithm to speech processingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975
- Minimum prediction residual principle applied to speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975
- The SIFT algorithm for fundamental frequency estimationIEEE Transactions on Audio and Electroacoustics, 1972
- System for Automatic Formant Analysis of Voiced SpeechThe Journal of the Acoustical Society of America, 1970
- Cepstrum Pitch DeterminationThe Journal of the Acoustical Society of America, 1967