![[CS logo]](../t.png)
CSPP 56553 - Artificial Intelligence
Winter 2004
Homework #6: Due March 3, 2004
Goals
Through this assignment you will:
- Explore Weighted Automata/Markov Models as a mechanism for reasoning with uncertainty over time.
- Experiment with the use of these models for pronunciation modeling and
speech recognition.
Non-Programming Alternative
Modeling Pronunciation
In lecture we discussed a model of the pronunciation of the word about
that had been extracted from the Switchboard corpus, a collection of
conversational telephone speech. Here we consider pronunciation from
a different data source - TIMIT - a phonetically structured corpus of
read speech. For TIMIT, participants were asked to a read back a set
of sentence prompts. These sentences were constructed to cause each
phoneme to appear in as many contexts as possible.
Below, you will see a set of pronunciations for the word "permanent"
automatically extracted from close manual phonetic transcriptions of
the TIMIT recordings. We will construct a weighted automaton model
of this word and use it to perform some calculations.
- pcl p er m ix nx eh n
- pcl p er m ix n ih n tcl t
- pcl p er m n ah n tcl t
- pcl p er m ix n eh q
- pcl p er m ix nx ix q
- pcl p er m n ih n tcl t
- pcl p er m ax nx ix n tcl t
- pcl p er m ah n eh n q
Part A
Identify the states and the legal transitions between states.
Part B
Compute the weights (transition probabilities) for each transition
in your automaton, based on the small corpus of pronunciations.
Part C
What is the probability of the pronunciation "pcl p er m ax nx ix n q"
according to the model? ('q' represents a glottal stop; it's not a typo)
Part D
Based on this automaton, what is the most probable pronunciation?
What is its probability?
Programming Alternative
Problem 1
Implement the Viterbi algorithm.
Apply your implementation to either the "tomato" or "about"
automata. Demonstrate the option of the algorithm on
two pronunciations.
Note: You only need to return the maximum
probability; you do not need to return the path (unless you
want the extra challenge).