DocumentCode :
967961
Title :
Unsupervised Pattern Discovery in Speech
Author :
Park, Alex S. ; Glass, James R.
Author_Institution :
Comput. Sci. & Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA
Volume :
16
Issue :
1
fYear :
2008
Firstpage :
186
Lastpage :
197
Abstract :
We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where the end goal is to classify speech into categories defined by a prespecified inventory of lexical units (i.e., phones or words). Instead, we attempt to discover such an inventory in an unsupervised manner by exploiting the structure of repeating patterns within the speech signal. We show how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream. Our approach to unsupervised word acquisition utilizes a segmental variant of a widely used dynamic programming technique, which allows us to find matching acoustic patterns between spoken utterances. By aggregating information about these matching patterns across audio streams, we demonstrate how to group similar acoustic sequences together to form clusters corresponding to lexical entities such as words and short multiword phrases. On a corpus of academic lecture material, we demonstrate that clusters found using this technique exhibit high purity and that many of the corresponding lexical identities are relevant to the underlying audio stream.
Keywords :
data mining; dynamic programming; pattern matching; speech processing; speech recognition; unsupervised learning; acoustic pattern matching; dynamic programming; lexical entity; speech recognition; speech signal processing; spoken utterance; unsupervised pattern discovery; untranscribed audio stream; Artificial intelligence; Automatic speech recognition; Computer science; Glass; Laboratories; Pattern matching; Sequences; Speech processing; Speech recognition; Streaming media; Speech processing; unsupervised pattern discovery; word acquisition;
fLanguage :
English
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1558-7916
Type :
jour
DOI :
10.1109/TASL.2007.909282
Filename :
4378402
Link To Document :
بازگشت