Wide context acoustic modeling in read vs. spontaneous speech
- 22 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1743-1746
- https://doi.org/10.1109/icassp.1997.598861
Abstract
Context-dependent acoustic models have been applied inspeech recognition research for many years, and have beenshown to increase the recognition accuracy significantly.The most common approach is to use triphones. Recently,several speech recognition groups have started investigatingthe use of larger phonetic context windows when buildingacoustic models. In this paper we discuss some of thecomputational problems arising from wide context modeling(polyphonic modeling) and present methods...Keywords
This publication has 4 references indexed in Scilit:
- The Karlsruhe-Verbmobil speech recognition enginePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Recognition of conversational telephone speech using the JANUS speech enginePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Improved decision trees for phonetic modelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Decision trees for phonological rules in continuous speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991