Abstract:A Bayesian adaptive procedure, the quick-auditory-filter (qAF) procedure, was used to estimate auditory-filter shapes that were asymmetric about their peaks. In three experiments, listeners who were naive to psychoacoustic experiments detected a fixed-level, pure-tone target presented with a spectrally notched noise masker. The qAF procedure adaptively manipulated the masker spectrum level and the position of the masker notch, which was optimized for the efficient estimation of the five parameters of an audito… Show more
“…An entropy-based criterion [12,13,14] is used for stimulus selection to maximize the information gain from each trial. After the th trial of the qBIF procedure, the band importance function is derived via logistic regression, and the performance for the next trial is predicted for all stimulus conditions according to (3).…”
Section: The Quick Band Importance Function (Qbif) Methodsmentioning
A speech intelligibility index (SII) based band importance function (BIF) for Mandarin monosyllabic words spoken by a female speaker was derived with an adaptive procedure in this work. The adaptive procedure, namely the quick-bandimportance-function (qBIF) procedure, optimized the stimulus on each trial according listeners' performance on proceeding trials in an iterative fashion. This method greatly improved the efficiency of data collection. Test-retest experiments were conducted and confirmed the reliability of this adaptive procedure at a group level. The BIF derived in this work showed generally consistence with the BIF derived with the traditional paradigm with noticeable differences at certain frequencies.
“…An entropy-based criterion [12,13,14] is used for stimulus selection to maximize the information gain from each trial. After the th trial of the qBIF procedure, the band importance function is derived via logistic regression, and the performance for the next trial is predicted for all stimulus conditions according to (3).…”
Section: The Quick Band Importance Function (Qbif) Methodsmentioning
A speech intelligibility index (SII) based band importance function (BIF) for Mandarin monosyllabic words spoken by a female speaker was derived with an adaptive procedure in this work. The adaptive procedure, namely the quick-bandimportance-function (qBIF) procedure, optimized the stimulus on each trial according listeners' performance on proceeding trials in an iterative fashion. This method greatly improved the efficiency of data collection. Test-retest experiments were conducted and confirmed the reliability of this adaptive procedure at a group level. The BIF derived in this work showed generally consistence with the BIF derived with the traditional paradigm with noticeable differences at certain frequencies.
“…This assumption is reflected in the SE covariance kernel chosen for the GP in the frequency dimension, which enforces a general smoothness (Rasmussen & Williams 2006). The tone detection probability estimate is produced by a posterior estimate of the function values given the observed data and learned hyperparameters, rather than the more typical case of optimizing over a set of parameters to best fit the observed data (Lesmes et al 2006; Shen & Richards 2013; Shen et al 2014). …”
Objectives
Pure-tone audiometry has been a staple of hearing assessments for decades. Many different procedures have been proposed for measuring thresholds with pure tones by systematically manipulating intensity one frequency at a time until a discrete threshold function is determined. The authors have developed a novel nonparametric approach for estimating a continuous threshold audiogram using Bayesian estimation and machine learning classification. The objective of this study is to assess the accuracy and reliability of this new method relative to a commonly used threshold measurement technique.
Design
The authors performed air conduction pure-tone audiometry on 21 participants between the ages of 18 and 90 years with varying degrees of hearing ability. Two repetitions of automated machine learning audiogram estimation and 1 repetition of conventional modified Hughson-Westlake ascending-descending audiogram estimation were acquired by an audiologist. The estimated hearing thresholds of these two techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz).
Results
The two threshold estimate methods delivered very similar estimates at standard audiogram frequencies. Specifically, the mean absolute difference between estimates was 4.16 ± 3.76 dB HL. The mean absolute difference between repeated measurements of the new machine learning procedure was 4.51 ± 4.45 dB HL. These values compare favorably to those of other threshold audiogram estimation procedures. Furthermore, the machine learning method generated threshold estimates from significantly fewer samples than the modified Hughson-Westlake procedure while returning a continuous threshold estimate as a function of frequency.
Conclusions
The new machine learning audiogram estimation technique produces continuous threshold audiogram estimates accurately, reliably, and efficiently, making it a strong candidate for widespread application in clinical and research audiometry.
“…Following the k th trial, the qBIF procedure optimizes the stimulus choice within the pool of possible stimuli. The optimization algorithm is based on an entropy-based criterion, such that the expected entropy for the posterior parameter distribution following the k + 1th trial would be minimized (see also Kontsevich & Tyler, 1999 ; Lesmes, Lu, Baek, & Albright, 2010 ; Shen & Richards, 2013a , 2013b ; Shen, Sivakumar, & Richards, 2014 ) where | P k +1′ | is the determinant of the covariance matrix for the parameter distribution following the k + 1th trial with the hypothetical stimulus specified by TMR′ and n ′; and E (.) indicates the expected value across the two possible responses (i.e., correct or incorrect) collected from the k + 1th trial.…”
Individual differences in the recognition of monosyllabic words, either in isolation (NU6 test) or in sentence context (SPIN test), were investigated under the theoretical framework of the speech intelligibility index (SII). An adaptive psychophysical procedure, namely the quick-band-importance-function procedure, was developed to enable the fitting of the SII model to individual listeners. Using this procedure, the band importance function (i.e., the relative weights of speech information across the spectrum) and the link function relating the SII to recognition scores can be simultaneously estimated while requiring only 200 to 300 trials of testing. Octave-frequency band importance functions and link functions were estimated separately for NU6 and SPIN materials from 30 normal-hearing listeners who were naïve to speech recognition experiments. For each type of speech material, considerable individual differences in the spectral weights were observed in some but not all frequency regions. At frequencies where the greatest intersubject variability was found, the spectral weights were correlated between the two speech materials, suggesting that the variability in spectral weights reflected listener-originated factors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.