Automated Measurement of Speech Recognition, Reaction Time, and Speech Rate and Their Relation to Self-Reported Listening Effort for Normal-Hearing and Hearing-Impaired Listeners Using various Maskers.

In speech audiometry, the speech-recognition threshold (SRT) is usually established by adjusting the signal-to-noise ratio (SNR) until 50% of the words or sentences are repeated correctly. However, these conditions are rarely encountered in everyday situations. Therefore, for a group of 15 young participants with normal hearing and a group of 12 older participants with hearing impairment, speech-recognition scores were determined at SRT and at four higher SNRs using several stationary and fluctuating maskers. Participants' verbal responses were recorded, and participants were asked to self-report their listening effort on a categorical scale (self-reported listening effort, SR-LE). The responses were analyzed using an Automatic Speech Recognizer (ASR) and compared to the results of a human examiner. An intraclass correlation coefficient of r = .993 for the agreement between their corresponding speech-recognition scores was observed. As expected, speech-recognition scores increased with increasing SNR and decreased with increasing SR-LE. However, differences between speech-recognition scores for fluctuating and stationary maskers were observed as a function of SNR, but not as a function of SR-LE. The verbal response time (VRT) and the response speech rate (RSR) of the listeners' responses were measured using an ASR. The participants with hearing impairment showed significantly lower RSRs and higher VRTs compared to the participants with normal hearing. These differences may be attributed to differences in age, hearing, or both. With increasing SR-LE, VRT increased and RSR decreased. The results show the possibility of deriving a behavioral measure, VRT, measured directly from participants' verbal responses during speech audiometry, as a proxy for SR-LE.

Automated Speech Audiometry for Integrated Voice Over Internet Protocol Communication Services.

PURPOSE: Problems in speech recognition are often apparent in telecommunication situations. For ecologically valid assessments of such conditions, it is important to quantify the impact of real environments including acoustic conditions at a far-end communication device and all paths of transmission degradation. This study presents an automated matrix sentence test procedure based on automatic speech recognition (ASR) integrated in a Voice over Internet Protocol (VoIP) infrastructure and compares the individual effects of transmission degradations with results from laboratory measurements. METHOD: Speech recognition thresholds (SRTs) were measured in 16 normal-hearing subjects in four test conditions: (a) a laboratory condition guided by a human experimenter, (b) a laboratory condition with reduced bandwidth and (c) additionally reduced headset quality to simulate typical communication systems, and (d) an automated, ASR-controlled adaptive test procedure over a real VoIP infrastructure. Errors of the ASR system were analyzed to show possible effects on measurement outcome Results: Measured SRTs showed a highly significant correlation (r = .93) between the fully automatic and "laboratory" conditions, with a constant bias of about 1 dB indicating a linear shift of the data without affecting the distribution around the mean. The individual impact of the different system degradations on SRTs could be quantified Conclusions: This study provides a proof of concept for automated ASR-based SRT measurements over VoIP systems for speech audiometric testing in real communication systems, as it produced results comparable to traditional laboratory settings for this group of 16 normal-hearing subjects. This makes VoIP services a promising candidate for speech audiometric testing in real communication systems.

Speech Audiometry at Home: Automated Listening Tests via Smart Speakers With Normal-Hearing and Hearing-Impaired Listeners.

Speech audiometry in noise based on sentence tests is an important diagnostic tool to assess listeners' speech recognition threshold (SRT), i.e., the signal-to-noise ratio corresponding to 50% intelligibility. The clinical standard measurement procedure requires a professional experimenter to record and evaluate the response (expert-conducted speech audiometry). The use of automatic speech recognition enables self-conducted measurements with an easy-to-use speech-based interface. This article compares self-conducted SRT measurements using smart speakers with expert-conducted laboratory measurements. With smart speakers, there is no control over the absolute presentation level, potential errors from the automated response logging, and room acoustics. We investigate the differences between highly controlled measurements in the laboratory and smart speaker-based tests for young normal-hearing (NH) listeners as well as for elderly NH, mildly and moderately hearing-impaired listeners in low, medium, and highly reverberant room acoustics. For the smart speaker setup, we observe an overall bias in the SRT result that depends on the hearing loss. The bias ranges from +0.7 dB for elderly moderately hearing-impaired listeners to +2.2 dB for young NH listeners. The intrasubject standard deviation is close to the clinical standard deviation (0.57/0.69 dB for the young/elderly NH compared with 0.5 dB observed for clinical tests and 0.93/1.09 dB for the mild/moderate hearing-impaired listeners compared with 0.9 dB). For detecting a clinically elevated SRT, the speech-based test achieves an area under the curve value of 0.95 and therefore seems promising for complementing clinical measurements.