<?xml version="1.0" standalone="yes"?>
<Paper uid="W94-0201">
  <Title>AUTOMATED TONE TRANSCRIPTION</Title>
  <Section position="8" start_page="11" end_page="11" type="concl">
    <SectionTitle>
CONCLUSION
</SectionTitle>
    <Paragraph position="0"> paper began with a discussion of the proof relating tone transcriptions to their phycounterparts, namely F0 traces. I showed it is desirable for phonologists working on tone to use sequences of F0 values as their primary data, rather than impressionistic transcriptions which make (usually implicit) assumptions about F0 scaling. I provided an F0 prediction function 'P which estimated the F0 value of a tone, given the F0 value of the previous tone a.nd the identities of the two tones. I presented instrumental data from Bamileke Dschang and showed how the function could be specialised for this language. The function was then incorporated into the evaluation functions of two implement~,d non-deterministic search algorithms. The performance results were encouraging and demonstrate the proraise of automated tone transcription.</Paragraph>
  </Section>
class="xml-element"></Paper>