Search

AbstractObjectiveDesignStudy sampleResultsConclusionsThis study was conducted to assess the ecological validity of the speech audiometry protocol recommended by Punch and Rakerd (2019) when implemented in older adults with hearing impairment. That protocol measures a listener’s speech recognition threshold (SRT), most comfortable loudness level for speech (MCL), and uncomfortable loudness level for speech (UCL) in an integrated format that utilises single spondaic words as the stimulus set for all tests.Stimulus presentation and response collection were fully automated, test times were tracked electronically, and a short questionnaire was administered to assess subjective reactions to the test procedures.The study participants were 12 older adults with bilaterally symmetrical sensorineural hearing loss.SRT measurements for both ears agreed well with the participants’ two-frequency pure tone averages, and MCL and UCL measurements agreed well with previously reported values for individuals with similar degrees of sensorineural hearing loss. The average time to complete bilateral speech audiometric testing was 13.1 minutes. Participants’ subjective reactions to the integrated protocol were highly positive.This study demonstrates that older listeners with sensorineural hearing loss can produce clinically acceptable speech audiometric results when testing is administered in an automated sequence prescribed by the integrated protocol. [ABSTRACT FROM AUTHOR]

ObjectiveAutomated speech recognition (ASR) systems have become increasingly sophisticated, accurate, and deployable on many digital devices, including on a smartphone. This pilot study aims to examine the speech recognition performance of ASR apps using audiological speech tests. In addition, we compare ASR speech recognition performance to normal hearing and hearing impaired listeners and evaluate if standard clinical audiological tests are a meaningful and quick measure of the performance of ASR apps.MethodsFour apps have been tested on a smartphone, respectively AVA, Earfy, Live Transcribe, and Speechy. The Dutch audiological speech tests performed were speech audiometry in quiet (Dutch CNC-test), Digits-in-Noise (DIN)-test with steady-state speech-shaped noise, sentences in quiet and in averaged long-term speech-shaped spectrum noise (Plomp-test). For comparison, the app's ability to transcribe a spoken dialogue (Dutch and English) was tested.ResultsAll apps scored at least 50% phonemes correct on the Dutch CNC-test for a conversational speech intensity level (65 dB SPL) and achieved 90–100% phoneme recognition at higher intensity levels. On the DIN-test, AVA and Live Transcribe had the lowest (best) signal-to-noise ratio +8 dB. The lowest signal-to-noise measured with the Plomp-test was +8 to 9 dB for Earfy (Android) and Live Transcribe (Android). Overall, the word error rate for the dialogue in English (19–34%) was lower (better) than for the Dutch dialogue (25–66%).ConclusionThe performance of the apps was limited on audiological tests that provide little linguistic context or use low signal to noise levels. For Dutch audiological speech tests in quiet, ASR apps performed similarly to a person with a moderate hearing loss. In noise, the ASR apps performed more poorly than most profoundly deaf people using a hearing aid or cochlear implant. Adding new performance metrics including the semantic difference as a function of SNR and reverberation time could help to monitor and further improve ASR performance.

Objective: Automated speech recognition (ASR) systems have become increasingly sophisticated, accurate, and deployable on many digital devices, including on a smartphone. This pilot study aims to examine the speech recognition performance of ASR apps using audiological speech tests. In addition, we compare ASR speech recognition performance to normal hearing and hearing impaired listeners and evaluate if standard clinical audiological tests are a meaningful and quick measure of the performance of ASR apps., Methods: Four apps have been tested on a smartphone, respectively AVA, Earfy, Live Transcribe, and Speechy. The Dutch audiological speech tests performed were speech audiometry in quiet (Dutch CNC-test), Digits-in-Noise (DIN)-test with steady-state speech-shaped noise, sentences in quiet and in averaged long-term speech-shaped spectrum noise (Plomp-test). For comparison, the app's ability to transcribe a spoken dialogue (Dutch and English) was tested., Results: All apps scored at least 50% phonemes correct on the Dutch CNC-test for a conversational speech intensity level (65 dB SPL) and achieved 90-100% phoneme recognition at higher intensity levels. On the DIN-test, AVA and Live Transcribe had the lowest (best) signal-to-noise ratio +8 dB. The lowest signal-to-noise measured with the Plomp-test was +8 to 9 dB for Earfy (Android) and Live Transcribe (Android). Overall, the word error rate for the dialogue in English (19-34%) was lower (better) than for the Dutch dialogue (25-66%)., Conclusion: The performance of the apps was limited on audiological tests that provide little linguistic context or use low signal to noise levels. For Dutch audiological speech tests in quiet, ASR apps performed similarly to a person with a moderate hearing loss. In noise, the ASR apps performed more poorly than most profoundly deaf people using a hearing aid or cochlear implant. Adding new performance metrics including the semantic difference as a function of SNR and reverberation time could help to monitor and further improve ASR performance., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Pragt, van Hengel, Grob and Wasmann.)