<?xml version="1.0" standalone="yes"?>
<Paper uid="P95-1001">
  <Title>Learning Phonological Rule Probabilities from Speech Corpora with Exploratory Computational Phonology</Title>
  <Section position="7" start_page="4" end_page="4" type="evalu">
    <SectionTitle>
3 Results
</SectionTitle>
    <Paragraph position="0"> We ran the estimation algorithm on 7203 sea, noes (129,864 words) read from the Wall Street Journal.</Paragraph>
    <Paragraph position="1"> The corpus (!993 WSJ Hub 2 (WSJ 0) training data) -consisted of 12 hours of speech, and had 8916 unique words. Table 6 shows the probabilities for the ten phonological rules described in SS2.2.</Paragraph>
    <Paragraph position="2"> Note that all of the rules are indeed quite optional; even the most commonly-employed rules, like flapping and h-voicing, only apply on average about 90% of the time. Many of the other rules, such as the reduced-vowel or reduced-liquid rules, only apply about 50% of the time.</Paragraph>
    <Paragraph position="3"> We next attempted to judge the reliability of our automatic rule-probability estimation algorithm by comparing it with hand transcribed pronunciations. We took the hand-transcribed pronunciations of each word in TIMIT, and computed rule probabilities by the same rule-tag counting procedure used for our forced-Viterbi output. Figure 7 shows the fit between the automatic and hand-transcribed probabilities. Since the TIMIT pronunciations were from a completely different data collection effort with a very different corpus and speakers, the closeness of the probabilities is quite encouraging.</Paragraph>
    <Paragraph position="4"> Figure 8 breaks down our automatically generated rule probabilities for the Wall Street Journal corpus  ities for Phonological Rules into male and female speakers. Notice that many of the rules seem to be employed more often by men than by women. For example, men are about 5% more likely to flap, more likely to reduce vowels ih ._.&amp;quot; 1 and er, and slightly more likely to reduce Lqums and nasals. --~ Since ~'- ~,~ese are coarticulation or fast-speech effects, our initial hypothesis was that the difference between male and female speakers was due to a faster speech-rate by males. By computing the weighted average seconds per phone for male and female speakers, we found that females had an average of 71 ms/phone, while males had an average of 68 ms/phone, a difference of about 4%, quite correlated with the similar differences in reduction and flapping.</Paragraph>
  </Section>
class="xml-element"></Paper>