Automated Forced-Choice Tests of Speech Recognition

Abstract

Purpose: This project was undertaken to develop automated tests of speech recognition, including speech-recognition threshold (SRT) and word-recognition test, using forced-choice responses and computerized scoring of responses. Specific aims were (1) to develop an automated method for measuring SRT for spondaic words that produces scores that are in close agreement with average pure-tone thresholds and (2) to develop an automated test of word recognition that distinguishes listeners with normal hearing from those with sensorineural hearing loss and which informs the hearing aid evaluation process.

Method: An automated SRT protocol was designed to converge on the lowest level at which the listener responds correctly to two out of two spondees presented monaurally. A word-recognition test was conducted with monosyllabic words (female speaker) presented monaurally at a fixed level. For each word, there were three rhyming foils, displayed on a touchscreen with the test word. The listeners touched the word they thought they heard. Participants were young listeners with normal hearing and listeners with sensorineural hearing loss. Words were also presented with nonrhyming foils and in an open-set paradigm. The open-set responses were scored by a graduate student research assistant.

Results: The SRT results agreed closely with the pure-tone average (PTA) obtained by automated audiometry. The agreement was similar to results obtained with the conventional SRT scoring method. Word-recognition scores were highest for the closed-set, nonrhyming lists and lowest for open-set responses. For the hearing loss participants, the scores varied widely. There was a moderate correlation between word-recognition scores and pure-tone thresholds which increased as more high frequencies were brought into the PTA. Based on the findings of this study, a clinical protocol was designed that determines if a listener's performance was in the normal range and if the listener benefited from increasing the level of the stimuli.

Conclusion: SRTs obtained using the automated procedure are comparable to the results obtained by the conventional clinical method that is in common use. The automated closed-set word-recognition test results show clear differentiation between scores for the normal and hearing loss groups. These procedures provide clinical test results that are not dependent on the availability of an audiologist to perform the tests.