Which Words Are Hard to Recognize? Prosodic, Lexical, and Disfluency Factors that Increase ASR Error Rates

Sharon Goldwater, Dan Jurafsky, Christopher D. Manning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Many factors are thought to increase the chances of misrecognizing a word in ASR, including low frequency, nearby disfluencies, short duration, and being at the start of a turn. However, few of these factors have been formally examined. This paper analyzes a variety of lexical, prosodic, and disfluency factors to determine which are likely to increase ASR error rates. Findings include the following. (1) For disfluencies, effects depend on the type of disfluency: errors increase by up to 15% (absolute) for words near fragments, but decrease by up to 7.2% (absolute) for words near repetitions. This decrease seems to be due to longer word duration. (2) For prosodic features, there are more errors for words with extreme values than words with typical values. (3) Although our results are based on output from a system with speaker adaptation, speaker differences are a major factor influencing error rates, and the effects of features such as frequency, pitch, and intensity may vary between speakers.
Original languageEnglish
Title of host publicationProceedings of ACL-08: HLT
Place of PublicationColumbus, Ohio
PublisherAssociation for Computational Linguistics
Pages380-388
Number of pages9
Publication statusPublished - 1 Jun 2008

Fingerprint

Dive into the research topics of 'Which Words Are Hard to Recognize? Prosodic, Lexical, and Disfluency Factors that Increase ASR Error Rates'. Together they form a unique fingerprint.

Cite this