Stochastic pronunciation modelling and soft match for out-of-vocabulary spoken term detection.

Dong Wang Simon King Joe Frankel Peter Bell

Published in: ICASSP (2010)

Keyphrases

spoken term detection
out of vocabulary
language model
broadcast news
speech recognition
automatic speech recognition

word segmentation
n gram
language modeling
cross language information retrieval
named entity recognition

query translation
search engine
named entities
text classification
previously unseen

semi supervised
hand crafted
parallel corpora
probabilistic model
hidden markov models