A joint decoding algorithm for multiple-example-based addition of words to a pronunciation lexicon
Dhananjay Bansal, Nishanth Ulhas Nair, Rita Singh, Bhiksha Raj · 2009
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.