Large vocabulary decoding and confidence estimation using word posterior probabilities
2002Vol. 3, pp. 1655–1658
Citations Over TimeTop 10% of 2002 papers
Abstract
The paper investigates the estimation of word posterior probabilities based on word lattices and presents applications of these posteriors in a large vocabulary speech recognition system. A novel approach to integrating these word posterior probability distributions into a conventional Viterbi decoder is presented. The problem of the robust estimation of confidence scores from word posteriors is examined and a method based on decision trees is suggested. The effectiveness of these techniques is demonstrated on the broadcast news and the conversational telephone speech corpora where improvements both in terms of word error rate and normalised cross entropy were achieved compared to the baseline HTK evaluation systems.
Related Papers
- → An effective simplifying scheme for Viterbi decoder(1991)13 cited
- → Implementation of the Modified State Mapping Viterbi Decoder with Radix-4(2006)2 cited
- → Analytical methods to determine internal precisions of Viterbi decoders(2003)
- → Parallel Processing Based Power Reduction in a 256 State Viterbi Decoder(2006)
- Research into the multi-constraint lengths Viterbi decode(2004)