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

Proceedings of ACL-08: HLT, pages 380–388, Columbus, Ohio, USA, June 2008. c⃝2008 Association for Computational Linguistics Which words are hard to recognize? Prosodic, lexical, and disfluency factors that increase ASR error rates Sharon Goldwater, Dan Jurafsky and Christopher D. Manning Department of Linguistics and Computer Science Stanford University {sgwater,jurafsky,manning}@stanford.edu Abstract 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 for- mally examined. This paper analyzes a variety of lexical, prosodic, and disfluency factors to determine which are likely to increase ASR er- ror rates. Findings include the following. (1) For disfluencies, effects depend on the type of disfluency: errors increase by up to 15% (ab- solute) for words near fragments, but decrease by up to 7.2% (absolute) for words near repeti- tions. 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. 1 Introduction In order to improve the performance of automatic speech recognition (ASR) systems on conversational speech, it is important to understand the factors that cause problems in recognizing words. Previous work on recognition of spontaneous monologues and dialogues has shown that infrequent words are more likely to be misrecognized (Fosler-Lussier and Morgan, 1999; Shinozaki and Furui, 2001) and that fast speech increases error rates (Siegler and Stern, 1995; Fosler-Lussier and Morgan, 1999; Shinozaki and Furui, 2001). Siegler and Stern (1995) and Shinozaki and Furui (2001) also found higher er- ror rates in very slow speech. Word length (in phones) has also been found to be a useful pre- dictor of higher error rates (Shinozaki and Furui, 2001). In Hirschberg et al.’s (2004) analysis of two human-computer dialogue systems, misrecog- nized turns were found to have (on average) higher maximum pitch and energy than correctly recog- nized turns. Results for speech rate were ambiguous: faster utterances had higher error rates in one corpus, but lower error rates in the other. Finally, Adda- Decker and Lamel (2005) demonstrated that both French and English ASR systems had more trouble with male speakers than female speakers, and found several possible explanations, including higher rates of disfluencies and more reduction. Many questions are left unanswered by these pre- vious studies. In the word-level analyses of Fosler- Lussier and Morgan (1999) and Shinozaki and Fu- rui (2001), only substitution and deletion errors were considered, so we do not know how including inser- tions might affect the results. Moreover, these stud- ies primarily analyzed lexical, rather than prosodic, factors. Hirschberg et al.’s (2004) work suggests that prosodic factors can impact error rates, but leaves open the question of which factors are …

Content truncated to 500 words