Automating Speech Audiometry in Quiet and in Noise Using a Deep Neural Network

In addition to pure-tone audiometry tests and electrophysiological tests, a comprehensive hearing evaluation includes assessing a subject's ability to understand speech in quiet and in noise. In fact, speech audiometry tests are commonly used in clinical practice; however, they are time-consuming as they require manual scoring by a hearing professional. To address this issue, we developed an automated speech recognition (ASR) system for scoring subject responses at the phonetic level. The ASR was built using a deep neural network and trained with pre-recorded French speech materials: Lafon's cochlear lists and Dodelé logatoms. Next, we tested the performance and reliability of the ASR in clinical settings with both normal-hearing and hearing-impaired listeners. Our findings indicate that the ASR's performance is statistically similar to manual scoring by expert hearing professionals, both in quiet and in noisy conditions. Moreover, the test-retest reliability of the automated scoring closely matches that of manual scoring. Together, our results validate the use of this deep neural network in both clinical and research contexts for conducting speech audiometry tests in quiet and in noise.