Speech recognition predictability of a Cantonese speech intelligibility index

Purpose Although the speech intelligibility index (SII) has been widely applied in the field of audiology and other related areas, application of this metric to cochlear implants (CIs) has yet to be investigated. In this study, SIIs for CI users were calculated to investigate whether the SII could be an effective tool for predicting speech perception performance in a population with CI. Method Fifteen pre- and postlingually deafened adults with CI participated. Speech recognition scores were measured using the AzBio sentence lists. CI users also completed questionnaires and performed psychoacoustic (spectral and temporal resolution) and cognitive function (digit span) tests. Obtained SIIs were compared with predicted SIIs using a transfer function curve. Correlation and regression analyses were conducted on perceptual and demographic predictor variables to investigate the association between these factors and speech perception performance. Result Because of the considerably poor hearing and large individual variability in performance, the SII did not predict speech performance for this CI group using the traditional calculation. However, new SII models were developed incorporating predictive factors, which improved the accuracy of SII predictions in listeners with CI. Conclusion Conventional SII models are not appropriate for predicting speech perception scores for CI users. Demographic variables (aided audibility and duration of deafness) and perceptual–cognitive skills (gap detection and auditory digit span outcomes) are needed to improve the use of the SII for listeners with CI. Future studies are needed to improve our CI-corrected SII model by considering additional predictive factors. Supplemental Material https://doi.org/10.23641/asha.8057003

Download Full-text

Modeling Binaural Unmasking of Speech Using a Blind Binaural Processing Stage

Trends in Hearing ◽

10.1177/2331216520975630 ◽

2020 ◽

Vol 24 ◽

pp. 233121652097563

Author(s):

Christopher F. Hauth ◽

Simon C. Berning ◽

Birger Kollmeier ◽

Thomas Brand

Keyword(s):

Speech Recognition ◽

Speech Intelligibility ◽

Single Channel ◽

Signal To Noise Ratio ◽

Binaural Processing ◽

Speech In Noise ◽

Masking Level Difference ◽

Low Pass ◽

Speech Intelligibility Index ◽

Filtered Speech

The equalization cancellation model is often used to predict the binaural masking level difference. Previously its application to speech in noise has required separate knowledge about the speech and noise signals to maximize the signal-to-noise ratio (SNR). Here, a novel, blind equalization cancellation model is introduced that can use the mixed signals. This approach does not require any assumptions about particular sound source directions. It uses different strategies for positive and negative SNRs, with the switching between the two steered by a blind decision stage utilizing modulation cues. The output of the model is a single-channel signal with enhanced SNR, which we analyzed using the speech intelligibility index to compare speech intelligibility predictions. In a first experiment, the model was tested on experimental data obtained in a scenario with spatially separated target and masker signals. Predicted speech recognition thresholds were in good agreement with measured speech recognition thresholds with a root mean square error less than 1 dB. A second experiment investigated signals at positive SNRs, which was achieved using time compressed and low-pass filtered speech. The results demonstrated that binaural unmasking of speech occurs at positive SNRs and that the modulation-based switching strategy can predict the experimental results.

Download Full-text

A Comparison of Personal Sound Amplification Products and Hearing Aids in Ecologically Relevant Test Environments

American Journal of Audiology ◽

10.1044/2018_aja-18-0027 ◽

2018 ◽

Vol 27 (4) ◽

pp. 581-593 ◽

Cited By ~ 11

Author(s):

Lisa Brody ◽

Yu-Hsiang Wu ◽

Elizabeth Stangl

Keyword(s):

Speech Recognition ◽

Hearing Aids ◽

Speech Intelligibility ◽

Best Practice ◽

Hearing Aid ◽

Recognition Performance ◽

Sound Quality ◽

Listening Effort ◽

Speech Intelligibility Index ◽

Sound Amplification

Purpose The aim of this study was to compare the benefit of self-adjusted personal sound amplification products (PSAPs) to audiologist-fitted hearing aids based on speech recognition, listening effort, and sound quality in ecologically relevant test conditions to estimate real-world effectiveness. Method Twenty-five older adults with bilateral mild-to-moderate hearing loss completed the single-blinded, crossover study. Participants underwent aided testing using 3 PSAPs and a traditional hearing aid, as well as unaided testing. PSAPs were adjusted based on participant preference, whereas the hearing aid was configured using best-practice verification protocols. Audibility provided by the devices was quantified using the Speech Intelligibility Index (American National Standards Institute, 2012). Outcome measures assessing speech recognition, listening effort, and sound quality were administered in ecologically relevant laboratory conditions designed to represent real-world speech listening situations. Results All devices significantly improved Speech Intelligibility Index compared to unaided listening, with the hearing aid providing more audibility than all PSAPs. Results further revealed that, in general, the hearing aid improved speech recognition performance and reduced listening effort significantly more than all PSAPs. Few differences in sound quality were observed between devices. All PSAPs improved speech recognition and listening effort compared to unaided testing. Conclusions Hearing aids fitted using best-practice verification protocols were capable of providing more aided audibility, better speech recognition performance, and lower listening effort compared to the PSAPs tested in the current study. Differences in sound quality between the devices were minimal. However, because all PSAPs tested in the study significantly improved participants' speech recognition performance and reduced listening effort compared to unaided listening, PSAPs could serve as a budget-friendly option for those who cannot afford traditional amplification.

Download Full-text

Accuracy of Speech Intelligibility Index Predictions for Noise-Masked Young Listeners With Normal Hearing and for Elderly Listeners With Hearing Impairment

Journal of Speech Language and Hearing Research ◽

10.1044/jshr.3801.234 ◽

1995 ◽

Vol 38 (1) ◽

pp. 234-243 ◽

Cited By ~ 28

Author(s):

Sarah E. Hargus ◽

Sandra Gordon-Salant

Keyword(s):

Speech Recognition ◽

Hearing Impairment ◽

Speech Intelligibility ◽

Predictive Accuracy ◽

Normal Hearing ◽

Auditory Sensitivity ◽

Test Conditions ◽

Speech Test ◽

Speech Intelligibility Index ◽

Speech Presentation

This study examined whether the accuracy of Speech Intelligibility Index (SII) predictions is affected by subject age when between-groups auditory sensitivity differences are controlled. SII predictive accuracy was assessed for elderly listeners with hearing impairment (EHI) and for young noise-masked listeners with normal hearing (NMN). SII predictive accuracy was poorer for the EHI subjects than for the NMN subjects across a range of test conditions and stimuli. Speech test redundancy, speech presentation level, signal-to-babble ratio, and babble level also affected SII predictive accuracy. The results suggest that the speech recognition difficulties experienced in noise by elderly listeners do not result solely from reduced auditory sensitivity.

Download Full-text