Title :
Unsupervised pronunciation validation
Author :
White, Christopher M. ; Sethy, Abhinav ; Ramabhadran, Bhuvana ; Wolfe, Patrick ; Cooper, Erica ; Saraclar, Murat ; Baker, James K.
Author_Institution :
HLT Center of Excellence, Johns Hopkins Univ., Baltimore, MN
Abstract :
This paper addresses selecting between candidate pronunciations for out-of-vocabulary words in speech processing tasks. We introduce a simple, unsupervised method that outperforms the conventional supervised method of forced alignment with a reference. The success of this method is independently demonstrated using three metrics from large-scale speech tasks: word error rates for large vocabulary continuous speech recognition, decision error tradeoff curves for spoken term detection, and phone error rates compared to a handcrafted pronunciation lexicon. The experiments were conducted using state-of-the-art recognition, indexing, and retrieval systems. The results were compared across many terms, hundreds of hours of speech, and well known data sets.
Keywords :
speech recognition; vocabulary; conventional supervised method; decision error tradeoff curve; out-of-vocabulary word; phone error rate; speech processing task; speech recognition; unsupervised pronunciation validation; word error rate; Acoustic measurements; Decision trees; Error analysis; Indexing; Iterative algorithms; Speech processing; Speech recognition; Speech synthesis; Testing; Vocabulary; Speech processing; Speech recognition; Speech synthesis;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2009.4960580