Generating word hypotheses in continuous speech
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 1565-1568
- https://doi.org/10.1109/icassp.1986.1168946
Abstract
This paper addresses the problem of generating word hypotheses in continuous German speech. It uses an extension of the well-known hidden Markow models in order to model more accurately the properties of the phonetic labeling stage. A powerful scoring function is derived. Experimental results are presented which were computed speaker independently.Keywords
This publication has 5 references indexed in Scilit:
- An algorithm for connected word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Isolated word recognition using hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A Maximum Likelihood Approach to Continuous Speech RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983
- A module for acoustic-phonetic transcription of fluently spoken German speechIEEE Transactions on Acoustics, Speech, and Signal Processing, 1982
- Review of the ARPA Speech Understanding ProjectThe Journal of the Acoustical Society of America, 1977