COMPUTER-ASSISTED PRONUNCIATION TEACHING BASED ON AUTOMATIC SPEECH RECOGNITION
S. M. Witt and S. J. Young
May 1997
Pronunciation teaching methods, as a part of computer assisted language learning systems, are currently limited in their ability to produce feedback on pronunciation quality. After an overview of previous work on pronunciation teaching, this article presents a pronunciation scoring algorithm based on automatic speech recognition, whereby scores at a phonemic level can be calculated. These ``goodness of pronunciation'' scores consist of a likelihood ratio between forced alignments and a maximum likelihood monophone loop. The results of evaluation experiments demonstrate the method's capability of detecting both individual mispronunciations as well as to give a general assessment of which sounds a student tends to pronounce badly.
If you have difficulty viewing files that end '.gz'
,
which are gzip compressed, then you may be able to find
tools to uncompress them at the gzip
web site.
If you have difficulty viewing files that are in PostScript, (ending
'.ps'
or '.ps.gz'
), then you may be able to
find tools to view them at
the gsview
web site.
We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.