Which words are hard to recognize? Prosodic, lexical, and disfluency factors that increase speech recognition error rates

Despite years of speech recognition research, little is known about which words tend to be misrecognized and why. Previous work has shown that errors increase for infrequent words, short words, and very loud or fast speech, but many other presumed causes of error (e.g., nearby disfluencies, turn-initial words, phonetic neighborhood density) have never been carefully tested. The reasons for the huge differences found in error rates between speakers also remain largely mysterious. Using a mixed-effects regression model, we investigate these and other factors by analyzing the errors of two state-of-the-art recognizers on conversational speech. Words with higher error rates include those with extreme prosodic characteristics, those occurring turninitially or as discourse markers, and doubly confusable pairs: acoustically similar words that also have similar language model probabilities. Words preceding disfluent interruption points (first repetition tokens and words before fragments) also...

• Type: Journal
• Year: 2010
• Where: SPEECH
• Authors: Sharon Goldwater, Daniel Jurafsky, Christopher D. Manning
• Keywords: Error Rate, Neighborhood Density, Phonetic Neighborhood, Security Privacy, SPEECH 2010