Objective measures of speech quality are highly desirable in benchmarking and monitoring the performance of hearing aids (HAs). Existing HA speech quality indices such as the hearing aid speech quality index (HASQI) are intrusive in that they require a properly time-aligned and frequency-shaped reference signal to predict the quality of HA output. Two new reference-free HA speech quality indices are proposed in this paper, based on a model that amalgamates perceptual linear prediction (PLP), hearing loss (HL) modeling, and machine learning concepts. For the first index, HL-modified PLP coefficients and their statistics were used as the feature set, which was subsequently mapped to the predicted quality scores using support vector regression (SVR). For the second index, HL-impacted gammatone auditory filterbank energies and their second-order statistics constituted the feature set, which was again mapped using SVR. Two databases involving HA recordings were collected and utilized for the evaluation of the robustness and generalizability of the two indices. Experimental results showed that the index based on the gammatone filterbank energies not only correlated well with HA quality ratings by hearing impaired listeners, but also exhibited robust performance across different test conditions and was comparable to the full-reference HASQI performance.

This study evaluated ratings of vocal strain and perceived listening effort by normal hearing participants while listening to speech samples produced by talkers with adductor spasmodic dysphonia (AdSD). In addition, objective listening effort was measured through concurrent pupillometry to determine whether listening to disordered voices changed arousal as a result of emotional state or cognitive load. Recordings of the second sentence of the “Rainbow Passage” produced by talkers with varying degrees of AdSD served as speech stimuli. Twenty naïve young adult listeners perceptually evaluated these stimuli on the dimensions of vocal strain and listening effort using two separate visual analogue scales. While making the auditory-perceptual judgments, listeners’ pupil characteristics were objectively measured in synchrony with the presentation of each voice stimulus. Data analyses revealed moderate-to-high inter- and intra-rater reliability. A significant positive correlation was found between the ratings of vocal strain and listening effort. In addition, listeners displayed greater peak pupil dilation (PPD) when listening to more strained and effortful voice samples. Findings from this study suggest that when combined with an auditory-perceptual task, non-volitional physiologic changes in pupil response may serve as an indicator of listening and cognitive effort or arousal.

This paper investigated the performance of a number of acoustic measures, both individually and in combination, in predicting the perceived quality of sustained vowels produced by people impaired with Parkinson’s disease (PD). Sustained vowel recordings were collected from 51 PD patients before and after the administration of the Levodopa medication. Subjective ratings of the overall vowel quality were garnered using a visual analog scale. These ratings served to benchmark the effectiveness of the acoustic measures. Acoustic predictors of the perceived vowel quality included the harmonics-to-noise ratio (HNR), smoothed cepstral peak prominence (CPP), recurrence period density entropy (RPDE), Gammatone frequency cepstral coefficients (GFCCs), linear prediction (LP) coefficients and their variants, and modulation spectrogram features. Linear regression (LR) and support vector regression (SVR) models were employed to assimilate multiple features. Different feature dimensionality reduction methods were investigated to avoid model overfitting and enhance the prediction capabilities for the test dataset. Results showed that the RPDE measure performed the best among all individual features, while a regression model incorporating a subset of features produced the best overall correlation of 0.80 between the predicted and actual vowel quality ratings. This model may therefore serve as a surrogate for auditory-perceptual assessment of Parkinsonian vowel quality. Furthermore, the model may offer the clinician a tool to predict who may benefit from Levodopa medication in terms of enhanced voice quality.

This paper evaluated the performance of an envelope enhancement (EE) algorithm subjectively by children with auditory processing disorder (APD), and objectively through computational models. Speech intelligibility data was collected from children with APD, for unprocessed and envelope-enhanced speech in the presence of stationary and non-stationary background noise at different signal to noise ratios (SNRs), both with and without noise reduction (NR) algorithms as a front-end to the EE algorithm. Furthermore, intrusive and non-intrusive objective speech intelligibility metrics were derived to predict the perceptual impact of this EE algorithm. Subjective data for stationary noise conditions revealed that the combination of NR and EE algorithms significantly improved the speech intelligibility scores at poor SNRs. In contrast, the same combination was ineffective in improving speech intelligibility in non-stationary noise conditions. Taken together, subjective results suggest that exaggerating the envelope cues improves speech identification scores for children with APD. However, the benefit obtained varies depending upon the type and level of the background noise. Both intrusive and non-intrusive objective speech intelligibility estimators exhibited good correlation with the subjective data, with the intrusive metric demonstrating better generalization capabilities. Implications of these results for hearing aid applications for children with APD is discussed.

Medical image processing applications typically demand highly accurate image segmentation. However, existing segmentation approaches exhibit performance degradation when faced with diverse medical imaging modalities and varied segmentation target sizes. In this paper, we propose and evaluate a dilated One-to-Many U-Net deep learning model that addresses these challenges. The proposed model comprises of four rows of encoder-decoder modules, with each module consisting of three trainable blocks with different layers. The last three rows of the U-Net are extended versions of the three blocks in the first row, with the encoder-decoder blocks connected through the skip connections to the previous rows. The outputs of the last blocks from the last three rows in the decoder are concatenated, and finally, a dilation network is employed to improve the small target segmentation in different medical images. Two datasets have been used for the evaluation: the HC18 grand challenge ultrasound dataset for fetal head segmentation and the Multi-site MRI dataset, including the BIDMC and HK sites, for prostate segmentation in MRI images. The proposed approach achieved Dice and Jaccard coefficients of 96.54% and 93.93%, respectively, for the HC18 grand challenge dataset, 96.76% and 93.97% for the BIDMC site dataset, and 92.58% and 86.96% for the HK site dataset. Statistical analyses showed that the proposed model outperformed several other U-Net-based models.

Objective measures of speech quality are attractive because they facilitate performance assessment of hearing aids (HAs) without the need for human listeners. Objective speech quality predictions are usually performed intrusively, wherein the “closeness” between the reference and HA output speech recordings is quantified. In this paper, we focus on nonintrusive estimation of HA speech quality based on Perceptual Linear Prediction (PLP) modeling approach. In PLP, perceptual phenomena such as non-uniform filter bank analysis and nonlinear mapping between sound intensity and its perceived loudness are incorporated into the linear prediction feature extraction process. In this work, PLP and PLP-based cepstral coefficients were computed from HA speech recordings and their statistical properties were utilized as features for speech quality estimation. A custom database of HA speech recordings obtained in different noisy and reverberant environments was used to investigate the predictive performance of these individual features. In addition, regression functions that linearly combined the features and mapped to the predicted quality scores, were derived and validated. Experimental results show that the proposed nonintrusive speech quality estimates correlate well with subjective ratings of speech quality by hearing impaired listeners.