A phonetic vocoder
- 13 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The authors study the problem of coding spectral information in speech at bit rates in the range of 100-400 b/s using speaker-independent phone-based recognition. Spectral information is coded as a sequence of phonetic events and a sequence of transitions through the corresponding hidden Markov model (HMM)-based phone models. This simple phonetic speech-coding system has been shown to be a promising approach. A simple inventory of phonemes is sufficient for capturing the bulk of the acoustic information Author(s) Picone, J. Texas Instrum. Inc., Dallas, TX, USA Doddington, G.R.Keywords
This publication has 4 references indexed in Scilit:
- Low rate speech coding using contour quantizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A comparison of methods for 300-400 b/s vocodersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- On modeling duration in context in speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The LPC trace as an HMM development toolThe Journal of the Acoustical Society of America, 1988