OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search

Automated Speech Audiometry: Can It Work Using Open-Source Pre-Trained Kaldi-NL Automatic Speech Recognition?

A practical speech audiometry tool is the digits-in-noise (DIN) test for hearing screening of populations of varying ages and hearing status. The test is usually conducted by a human supervisor (e.g., clinician), who scores the responses spoken by the listener, or online, where software scores the responses entered by the listener. The test has 24-digit triplets presented in an adaptive staircase procedure, resulting in a speech reception threshold (SRT). We propose an alternative automated DIN test setup that can evaluate spoken responses whilst conducted without a human supervisor, using the open-source automatic speech recognition toolkit, Kaldi-NL. Thirty self-reported normal-hearing Dutch adults (19-64 years) completed one DIN + Kaldi-NL test. Their spoken responses were recorded and used for evaluating the transcript of decoded responses by Kaldi-NL. Study 1 evaluated the Kaldi-NL performance through its word error rate (WER), percentage of summed decoding errors regarding only digits found in the transcript compared to the total number of digits present in the spoken responses. Average WER across participants was 5.0% (range 0-48%, SD = 8.8%), with average decoding errors in three triplets per participant. Study 2 analyzed the effect that triplets with decoding errors from Kaldi-NL had on the DIN test output (SRT), using bootstrapping simulations. Previous research indicated 0.70 dB as the typical within-subject SRT variability for normal-hearing adults. Study 2 showed that up to four triplets with decoding errors produce SRT variations within this range, suggesting that our proposed setup could be feasible for clinical applications.

Update on surgical and nonsurgical treatment options for age-related hearing loss

BACKGROUND

Age-related hearing loss (ARHL) is one of the most common chronic conditions that impacts on everyday life far beyonds speech understanding. Chronic hearing loss has been associated with social isolation, depression, and cognitive decline. Early diagnosis and appropriate treatment are recommended.

OBJECTIVE

To give an overview of surgical and non-surgical treatment options for ARHL and the gap between the high prevalence of ARHL and its inadequate treatment to date.

MATERIAL AND METHODS

A selective literature search was carried out in PubMed.

RESULTS

In case of mild to moderate hearing loss, provision of air conduction hearing aids is still the method of choice as it leads to a large benefit in speech understanding and hearing-specific quality of life, and to a slight improvement in overall quality of life. Implantable middle ear systems are used for the treatment of special types of hearing impairment. In case of severe to profound hearing loss, cochlear implantation should be considered; however, only a small number of older people with hearing loss are supplied with hearing aids or cochlear implants despite the well-known benefits of both. This also applies to high-income countries where the costs are covered by health insurance funds.

CONCLUSION

Considering the low rate of properly treated people with hearing loss, large-scale screening programs, including better counselling of older people, should be developed.

Using Automatic Speech Recognition to Optimize Hearing-Aid Time Constants

Automatic speech recognition (ASR), when combined with hearing-aid (HA) and hearing-loss (HL) simulations, can predict aided speech-identification performances of persons with age-related hearing loss. ASR can thus be used to evaluate different HA configurations, such as combinations of insertion-gain functions and compression thresholds, in order to optimize HA fitting for a given person. The present study investigated whether, after fixing compression thresholds and insertion gains, a random-search algorithm could be used to optimize time constants (i.e., attack and release times) for 12 audiometric profiles. The insertion gains were either those recommended by the CAM2 prescription rule or those optimized using ASR, while compression thresholds were always optimized using ASR. For each audiometric profile, the random-search algorithm was used to vary time constants with the aim to maximize ASR performance. A HA simulator and a HL simulator simulator were used, respectively, to amplify and to degrade speech stimuli according to the input audiogram. The resulting speech signals were fed to an ASR system for recognition. For each audiogram, 1,000 iterations of the random-search algorithm were used to find the time-constant configuration yielding the highest ASR score. To assess the reproducibility of the results, the random search algorithm was run twice. Optimizing the time constants significantly improved the ASR scores when CAM2 insertion gains were used, but not when using ASR-based gains. Repeating the random search yielded similar ASR scores, but different time-constant configurations.