InterSpeech 2021

Analysis and Tuning of a Voice Assistant System for Dysfluent Speech
(Oral presentation)

Vikramjit Mitra (Apple, USA), Zifang Huang (Apple, USA), Colin Lea (Apple, USA), Lauren Tooley (Apple, USA), Sarah Wu (Apple, USA), Darren Botten (Apple, USA), Ashwini Palekar (Apple, USA), Shrinath Thelapurath (Apple, USA), Panayiotis Georgiou (Apple, USA), Sachin Kajarekar (Apple, USA), Jefferey Bigham (Apple, USA)
Dysfluencies and variations in speech pronunciation can severely degrade speech recognition performance, and for many individuals with moderate-to-severe speech disorders, voice operated systems do not work. Current speech recognition systems are trained primarily with data from fluent speakers and as a consequence do not generalize well to speech with dysfluencies such as sound or word repetitions, sound prolongations, or audible blocks. The focus of this work is on quantitative analysis of a consumer speech recognition system on individuals who stutter and production-oriented approaches for improving performance for common voice assistant tasks (i.e., “what is the weather?”). At baseline, this system introduces a significant number of insertion and substitution errors resulting in intended speech Word Error Rates (isWER) that are 13.64% worse (absolute) for individuals with fluency disorders. We show that by simply tuning the decoding parameters in an existing hybrid speech recognition system one can improve isWER by 24% (relative) for individuals with fluency disorders. Tuning these parameters translates to 3.6% better domain recognition and 1.7% better intent recognition relative to the default setup for the 18 study participants across all stuttering severities.