Automatic Speech Recognition Services: Deaf and Hard-of-Hearing Usability
This addresses the accessibility problem for DHH people in using speech interfaces, but it appears incremental as it focuses on evaluating existing methods rather than proposing new solutions.
The paper evaluated the performance of Automatic Speech Recognition (ASR) services for Deaf and Hard-of-Hearing (DHH) speakers, finding that while ASR can achieve Word Error Rates as low as 5-6% with custom vocabulary models, it often fails to be accessible for DHH users.
Nowadays, speech is becoming a more common, if not standard, interface to technology. This can be seen in the trend of technology changes over the years. Increasingly, voice is used to control programs, appliances and personal devices within homes, cars, workplaces, and public spaces through smartphones and home assistant devices using Amazon's Alexa, Google's Assistant and Apple's Siri, and other proliferating technologies. However, most speech interfaces are not accessible for Deaf and Hard-of-Hearing (DHH) people. In this paper, performances of current Automatic Speech Recognition (ASR) with voices of DHH speakers are evaluated. ASR has improved over the years, and is able to reach Word Error Rates (WER) as low as 5-6% [1][2][3], with the help of cloud-computing and machine learning algorithms that take in custom vocabulary models. In this paper, a custom vocabulary model is used, and the significance of the improvement is evaluated when using DHH speech.