Homework 1
Out: Feb-16 Due: Feb-22 Thursday night (12:00)

Send your answers in using the hand-in box on the speech labs homepage.

your script count.tcl and output of Task 1-1
your answer and output of Question 1-1
Write a program countPairs.tcl which reads in a text file and counts the occuring word pairs. The program outputs the list of different words pairs together with the number of occurences (separated by blanks). Use the existing program count.tcl as sample. Caution: Like in count.tcl the utteranceID should not be considered as a word. For calculating the number of word pairs we would like to which words occur at the beginning or the end of an utterance. Therefore, we define the character <s> to be the marker of the beginning of an utterance, and </s> to be the marker of the end of an utterance. The sentence:

THE PLANTS WILTED AND DIED

consists of the following word pairs:
<s> , THE
THE , PLANTS
PLANTS , WILTED
WILTED , AND
AND , DIED
DIED , </s>

Run the program with
tools/countPairs.tcl steps/data/transcripts
Hand in countPairs.tcl

your answer and output of Question 2-1 to Question 2-6

Last modified: Fri Feb 16 15:00:20 EST 2001
Maintainer: tanja@cs.cmu.edu.