DocumentCode
3529109
Title
A joint decoding algorithm for multiple-example-based addition of words to a pronunciation lexicon
Author
Bansal, Dhananjay ; Nair, Nishanth ; Singh, Rita ; Raj, Bhiksha
Author_Institution
Xtone Networks, Reston, VA
fYear
2009
fDate
19-24 April 2009
Firstpage
4293
Lastpage
4296
Abstract
We propose an algorithm that enables joint Viterbi decoding of multiple independent audio recordings of a word to derive its pronunciation. Experiments show that this method results in better pronunciation estimation and word recognition accuracy than that obtained either with a single example of the word or using conventional approaches to pronunciation estimation using multiple examples.
Keywords
Viterbi decoding; speech coding; speech recognition; independent audio recordings; joint Viterbi decoding; joint decoding algorithm; pronunciation estimation; pronunciation lexicon; speech recognition systems; word recognition accuracy; words multiple-example-based addition; Audio recording; Automatic speech recognition; Bayesian methods; Decoding; Hidden Markov models; Lattices; Probability distribution; Speech recognition; US Department of Transportation; Viterbi algorithm; Joint decoding; Pronunciation estimation; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location
Taipei
ISSN
1520-6149
Print_ISBN
978-1-4244-2353-8
Electronic_ISBN
1520-6149
Type
conf
DOI
10.1109/ICASSP.2009.4960578
Filename
4960578
Link To Document