1 |
Self-conducted speech audiometry using automatic speech recognition
|
|
|
|
Abstract:
Speech-in-noise tests are an important tool for assessing the speech recognition ability of a listener. While several well-established clinical measurement procedures exist, most come with the drawback of a high measurement effort, since a specialist needs to conduct the speech audiometric test. This work addresses this issue by proposing self-measurement applications utilizing automatic speech recognition (ASR). Two different application scenarios are considered: a well-controlled laboratory environment with a locally running ASR system developed specifically for this purpose and a screening application using the ASR component of a smart speaker - i.e., a commercially available high-quality speaker connected to a virtual assistant. The two systems proposed are evaluated with 139 subjects in total - covering a wide range of hearing abilities: normal-hearing listeners, mildly-, moderately- and severely hearing-impaired subjects, as well as listeners with cochlear implants. The measurement accuracy with the unsupervised procedure was found to be in the same range as when conducting the test with a human supervisor.
|
|
Keyword:
Computer science; internet; Medicine and health
|
|
URL: http://oops.uni-oldenburg.de/5143/7/Ooster_Dissertation.pdf http://oops.uni-oldenburg.de/5143/
|
|
BASE
|
|
Hide details
|
|
2 |
Speech Audiometry at Home: Automated Listening Tests via Smart Speakers With Normal-Hearing and Hearing-Impaired Listeners
|
|
|
|
In: Trends Hear (2020)
|
|
BASE
|
|
Show details
|
|
|
|