Talk Abstract:
Seminar
on Industrial Problems
Language Modeling for an Application of Large Vocabulary Speech
Recognition
February 19, 1999
Presented
by:
Joan Bachenko
Linguistic Technologies, Inc.
The talk will be held at 570 Vincent Hall
10:10 am
Automatic speech recognition systems work by using sophisticated
pattern matching software to find the best fit between a speech
waveform and a string of words. The pattern matcher is driven
by two data components: acoustic models, which provide the pattern
matcher with probabilistic representations of speech sounds
and contexts, and the language model, which incorporates a dictionary
of words and pronunciations plus a stochastic grammar that encodes
the likelihood of word contexts. In this talk, I will describe
a dictation application of speech recognition. The application
is interesting because, in addition to its commercial value,
it offers challenges to language modeling that have not been
well studied in the technical community. I will provide a brief
outline of the main technical issues and then discuss a novel
approach to language modeling that Linguistic Technologies has
developed for making this application feasible.
