Very large vocabulary isolated utterance recognition: a comparison between one pass and two pass strategies
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A system for recognizing isolated utterances belonging to a very large vocabulary is presented that follows a two-pass strategy. The first step, hypothesization, consists in the selection of a subset of word candidates, starting from the segmentation of speech into six broad phonetic classes. This module is implemented through a dynamic programming algorithm working in a three-dimensional space. The search is performed on a tree representing a coarse description of the lexicon. The second step is the search for the best N candidates according to a maximum-likelihood criterion. Each word candidate is represented by a graph of subword hidden Markov models, and a tree structure of the whole word subset is built on line for an efficient implementation of the Viterbi algorithm. A comparison with a direct approach that does not use the hypothesization module shows that the two-pass approach has the same performance with an 80% reduction in computational complexity.Keywords
This publication has 7 references indexed in Scilit:
- Word preselection for large vocabulary speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A model of lexical access from partial phonetic informationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Definition and evaluation of phonetic units for speech recognition by hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Generating word hypotheses in continuous speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Interaction between fast lexical access and word verification in large vocabulary continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Experimental results on large-vocabulary continuous speech recognition and understandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A segmentation algorithm for connected word recognition based on estimation principlesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1983