Auditory Spectrum Research Articles

Beyond breathalyzers: AI-powered speech analysis for alcohol intoxication detection

Detecting potential alcohol inebriation or intoxication status holds paramount significance for social prevention and security. Beyond its association with long-term health effects, alcohol consumption can lead to immediate consequences, including reduced control over one’s actions, with traffic fatalities representing one of the most tragic outcomes.This study leveraged the Alcohol Language corpus, involving 162 subjects recorded both in sober and inebriated states. Participants provided 60 speech samples while sober and 30 when intoxicated, all within a realistic car setting using head-mounted microphones. Our research endeavors encompassed comprehensive stratified statistical tests to examine the impact of alcohol consumption on speech production while uncovering the influence of covariates such as age, gender, and drinking habits.Additionally, we introduced a speaker-neutral machine learning algorithm, based on the Domain-Adversarial Neural Network architecture. This approach aimed to overcome challenges posed by individual differences that often complicate intoxicated speech analysis. Notably, our findings highlighted the effectiveness of features like the RASTA-filtered auditory spectrum. Nevertheless, the results from statistical tests emphasized the need for techniques that minimize inter-subject variability.As for the automatic classification, the proposed architecture exhibited promising results, yielding a classification accuracy slightly exceeding 70% on an independent test set. Although preliminary, our research demonstrates the potential for detecting alcohol-induced speech changes, benefiting societal well-being and security. It also underscores the importance of developing strategies that account for individual differences while harnessing the power of automatic models to effectively distinguish between sober and intoxicated individuals.

Categorization of pickleball paddles as a highly impulsive sound source

As the sport of pickleball has grown in popularity and tennis courts close to homes are being converted to this use, noise regulation for pickleball courts has become a topic of discussion among city councils, planners, home owners associations, residents, and, increasingly, attorneys seeking injunctions against poorly sited or mitigated courts. Accurate noise impact assessment of the short duration impulsive sound produced by the impact of the ball on the paddles requires the use of the highly impulsive adjustment in ANSI S12.9 Part 4. Examination of the definitions of impulsive sound in this standard and in ISO 1996 Part 1 identifies characteristics of rapid onset, significant energy in the most sensitive part of the auditory spectrum, and duration as primary differentiators for categorization. The noise impact assessment methodology in ANSI S12.9 Part 4 for highly impulsive sound has proven an effective means of determining the amount of mitigation needed for pickleball facilities, being more repeatable and precise than other commonly used assessment methods while avoiding underestimation of annoyance.

Newborn Hearing Screening with Two-Step Protocol and Risk Factor Identification: Our Experience at a Tertiary Care Centre in Eastern India.

To estimate the prevalence of hearing loss and identify the high-risk factors among neonates with hearing loss. Retrospective study done on 1054 infants in a tertiary care centre in Eastern India from 2020 to 2021 and approved by the Institutional Ethics Committee. A two-step protocol is used for screening. In the well-nursed group, OAE and BOA were performed. In the case of REFER results for automated ABR following OAE evaluation in well-nursed babies, a detailed audiological evaluation was scheduled to be carried out using diagnostic ABR within one month of age. In the high-risk group, hearing screening includes OAE, BOA, and AABR evaluations. AABR evaluation was performed as a part of the screening protocol irrespective of the results of OAE screening as PASS or REFER. In our study among 1053 neonates screened, 375 were in the risk category, and 679 were without risk factors. The overall prevalence of hearing loss in neonates was 22.78 per 1000 screened neonates and 56 per 1000 among high-risk neonates. In the high-risk group, we were able to identify 4 cases of Auditory spectrum neuropathy disorder with the use of AABR during 1st step of screening. In multivariate regression analysis, the risk factors for hearing loss identified were NICU stay (OR = 3.6, 95% CI = 1.1-12.03) and Craniofacial anomalies (OR = 55.37, 95% CI = 16.48- 186.01). Early neonatal screening helps in the detection, intervention, and rehabilitation of hearing loss. The use of AABR in risk infant screening enhanced the chance of detection of auditory spectrum neuropathy disorder (ASND) cases. The online version contains supplementary material available at 10.1007/s12070-023-03723-3.

Measures of music-like experience emergent in a sonic Ganzfeld: An example of perceptual structuring on the edge of silence.

We conducted an experiment in which participants listened to a semi-stochastic stream of acoustic data, during which they reported regular variations in melody, pitch and rhythm that are not physically present in the stimulus. In addition, the occurrence of particular forms (melodies and rhythms) and pitches appear to be associated with the occurrence of others. This indicates that a complex taxonomy of subjective auditory experience can be evoked in observers given small variation in the quality of noise along the auditory spectrum. It also strongly indicates that when experiencing "noise," our automatic response is to restructure this such that it becomes "perceptually" meaningful. In an environment where there is no sound, neural systems will reduce their engagement, and will respond semi stochastically. Taken alongside our data, this tends to suggest that one consequence of "silence" might be a tendency to spontaneously hallucinate complex and well-structured auditory experience based solely upon the stochastic neural response to the absence of sound. This paper describes the type of experience one might have on the "edge of silence" and discusses some of the associated implications.

Weld penetration identification with deep learning method based on auditory spectrum images of arc sounds

Weld penetration identification with deep learning method based on auditory spectrum images of arc sounds

Nonspecific hebbian neural network model predicts musical scales discreteness and just intonation without using octave-equivalency mapping

This study continues investigating the consonance-pattern emerging neural network model introduced in our previous publication, specifically to test if it will reproduce the results using 100-fold finer precision of 1/100th of a semitone (1 cent). The model is a simplistic feed-forward generic Hebbian-learning generic neural network trained with multiple-harmonic complex sounds from the full auditory sound spectrum of 10 octaves. We use the synaptic weights between the neural correlates of each two-tone from the said spectrum to measure the model’s preference to their inter-tonal interval (12,0002 intervals), considering familiarity as a consonance predictor. We analyze all the 12,000 intervals of a selected tone (the tonic), and the results reveal three distinct yet related features. Firstly, Helmholtz’s list of consonant intervals re-emerges from the synaptic weights of the model, although with disordered dissonant intervals. Additionally, the results show a high preference to a small number of selected intervals, mapping the virtually continual input sound spectrum to a discrete set of intervals. Finally, the model's most preferred (most consonant) intervals are from the Just Intonation scales. The model does not need to use cross-octave interval mapping due to octave equivalence to produce the said results.

Human auditory frequency discrimination and inter-stimulus interval

The goal of this study was to determine how human performance in discriminating between similar frequencies in the auditory spectrum was influenced by modifying the interstimulus interval (ISI). The ISI is defined as the time elapsed from the end of the first stimulus and the beginning of the second stimulus. The relationship between ISI and auditory discrimination was explored using an auditory file comprised of 40 tests that each contained two tones with a frequency difference of 1%. For each test, 44 participants were asked to select the tone they perceived as being a higher frequency. The two frequencies used in each test were centered around one of five base frequencies, and the ISI used in each test was one of eight predetermined intervals. Results from previous auditory frequency discrimination studies regarding the just-noticeable difference (JND) and Weber’s law were used in the selection of the frequency difference of 1% that was used in this experiment. This frequency difference was kept constant across all the tests in order to ensure that the ISI was the main factor influencing participant performance. Participant performance was greatest at an ISI of 1000 ms when results were averaged by frequency. Additionally, as the base frequency increased, average performance generally improved. The findings from this experiment promote further investigation into the effects of varying ISI on the integration of auditory information by the auditory cortex.

Coal gangue recognition using multichannel auditory spectrogram of hydraulic support sound in convolutional neural network

Many data-driven coal gangue recognition (CGR) methods based on the vibration or sound of collapsed coal and gangue have been proposed to achieve automatic CGR, which is important for realizing intelligent top-coal caving. However, the strong background noise and complex environment in underground coal mines render this task challenging in practical applications. Inspired by the fact that workers distinguish coal and gangue from underground noise by listening to the hydraulic support sound, we propose an auditory model based CGR method that simulates human auditory recognition by combining an auditory spectrogram with a convolutional neural network (CNN). First, we adjust the characteristic frequency (CF) distribution of the auditory peripheral model (APM) based on the spectral characteristics of collapsed sound signals from coal and gangue and then process the sound signals using the adjusted APM to obtain inferior colliculus auditory signals with multiple CFs. Subsequently, the auditory signals of all CFs are converted into gray images separately and then concatenated into a multichannel auditory spectrum (MCAS) along the channel dimension. Finally, we input the MCAS as a feature map to the two-dimensional CNN, whose convolutional layers are used to automatically extract features, and the fully connected layer and softmax layer are used to flatten features and predict the recognition result, respectively. The CNN is optimized for the CGR based on a comparison study of four typical types of CNN structures with different network training hyperparameters. The experimental results show that this method affords an accurate CGR with a recognition accuracy of 99.5%. Moreover, this method offers excellent noise immunity compared with typically used CGR methods under various noisy conditions.

Neural presbycusis at ultra-high frequency in aged common marmosets and rhesus monkeys.

The aging of the population and environmental noise have contributed to high rates of presbycusis, also known as age-related hearing loss (ARHL). Because mice have a relatively short life span, murine models have not been suitable for determining the mechanism of presbycusis development and methods of diagnosis. Although the common marmoset, a non-human primate (NHP), is an ideal animal model for studying age-related diseases, its auditory spectrum has not been systematically studied. Auditory brainstem responses (ABRs) from 38 marmosets of different ages demonstrated that auditory function correlated with age. Hearing loss in geriatric common marmosets started at ultra-high frequency (>16 kHz), then extended to lower frequencies. Despite age-related deterioration of ABR threshold and amplitude in marmosets, outer hair cell (OHC) function remained stable at all ages. Spiral ganglion neurons (SGNs), which are the first auditory neurons in the auditory system, were found to degenerate distinctly in aged common marmosets, indicating that neural degeneration caused presbycusis in these animals. Similarly, age-associated ABR deterioration without loss of OHC function was observed in another NHP, rhesus monkeys. Audiometry results from these two species of NHP suggested that NHPs were ideal for studying ARHL and that neural presbycusis at high frequency may be prevalent in primates.

Modifying auditory perception with prisms? Aftereffects of prism adaptation on a wide auditory spectrum in musicians and nonmusicians

Prism adaptation consists of pointing to visual targets while wearing prisms that shift the visual field laterally. The aftereffects are not restricted to sensorimotor level but extend to spatial cognition. There is a link between spatial representation and auditory frequency, with an association of low frequencies on the left side and high frequencies on the right side of space. The present study aimed first at evaluating the representation of auditory frequencies on a wide range of frequencies in musicians and nonmusicians. We used the ‘auditory interval bisection judgment’ within three auditory intervals. The results showed a pseudoneglect behavior in pretest in musicians and nonmusicians for high frequency intervals, reflecting a perceptual bias of the subjective interval center toward lower frequencies. The second aim of the present study was to evaluate the aftereffects of prism adaptation on an expanded auditory spectrum. The results showed aftereffects of adaptation to a leftward optical deviation for high frequency intervals in musicians and nonmusicians. Adaptation to a leftward optical deviation affects the auditory perception on an extended auditory spectrum, by shifting the subjective interval center toward high frequencies. The present study provides innovative data about representation of auditory perception and its modulation by prism adaptation.

A Feature Extraction Method Using Auditory Nerve Response for Collapsing Coal-Gangue Recognition

To intelligentize the top-coal caving’s process, many data-driven coal-gangue recognition techniques have been proposed recently. However, practical applications of these techniques are hindered by coal mine underground’s high background noise and complex environment. Considering that workers distinguish coal and gangue by hearing the impact sounds on the hydraulic support, we proposed a novel feature extraction method based on an auditory nerve (AN) response model simulating the human auditory system. Firstly, vibration signals were measured by an acceleration sensor mounted on the back of the hydraulic support’s tail beam, and then they were converted into acoustic pressure signals. Secondly, an AN response model of different characteristic frequencies was applied to process these signals, whose output constituted the auditory spectrum for feature extraction. Meanwhile, a feature selection method integrated with variance was used to reduce redundant information of the original features. Finally, a support vector machine was employed as the classifier model in this work. The proposed method was tested and evaluated on experimental datasets collected from the Tashan Coal Mine in China. In addition, its recognition accuracy was compared with other coal-gangue recognition methods based on commonly used features. The results show that our proposed method can reach a superior recognition accuracy of 99.23% and presents better generalization ability.

Late fusion framework for Acoustic Scene Classification using LPCC, SCMC, and log-Mel band energies with Deep Neural Networks

A major problem in Acoustic Scene Classification (ASC) is a representation of an acoustic scene, which serves to be an important task for ASC. This study used Linear Prediction Cepstral Coefficients (LPCC) and Spectral Centroid Magnitude Cepstral Coefficients (SCMC) features along with log-Mel band energies for the representation of an acoustic scene. Deep Neural Networks (DNN) is being used to model the Acoustic Scene Classification (ASC). LPCCs are used to capture the changes in the auditory spectrum with time and SCMCs are used to capture the weighted average magnitude finely for a given acoustic scene subband. log-Mel band energies are used to capture the spectral envelopes of audio frame. The DNN architecture is used for audio track level classification. We have experimented on Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 development dataset and DCASE 2017 dataset. We carried out experiments with individual feature sets, and also performed decision level DNN score fusions for improving the performance.

Periodicity Pitch Perception.

This study presents a computational model to reproduce the biological dynamics of “listening to music.” A biologically plausible model of periodicity pitch detection is proposed and simulated. Periodicity pitch is computed across a range of the auditory spectrum. Periodicity pitch is detected from subsets of activated auditory nerve fibers (ANFs). These activate connected model octopus cells, which trigger model neurons detecting onsets and offsets; thence model interval-tuned neurons are innervated at the right interval times; and finally, a set of common interval-detecting neurons indicate pitch. Octopus cells rhythmically spike with the pitch periodicity of the sound. Batteries of interval-tuned neurons stopwatch-like measure the inter-spike intervals of the octopus cells by coding interval durations as first spike latencies (FSLs). The FSL-triggered spikes synchronously coincide through a monolayer spiking neural network at the corresponding receiver pitch neurons.

P07-F Event related EEG brain oscillations differentiate cognitive decline in patients with Parkinson’s disease

Background Studies on Event Related EEG Brain Oscillations presented essential results on the understanding of cognitive brain function and cognitive decline in different pathologies. Event related oscillatory dynamics in Parkinson’s disease (PD) have not been studied comprehensively. In the last three years, our group aimed to fulfill this critical gap. Material and methods 27 PD patients without cognitive deficits, 34 PD patients with Mild Cognitive Impairment, 22 patients with PD Dementia and 33 healthy controls were included in the study.EEG was recorded during visual and auditory oddball paradigEvent related power spectrum, phase locking, event related coherence were evaluated in delta, theta, alpha, beta and gamma frequency bands for all group of subjects. Results Event related delta, theta, alpha and beta power and phase locking increased with a cognitive load in healthy subjects but these responses decreased in PD patients who have mild cognitive impairment and dementia. Event related delta, theta, and alpha coherence values were also lower in PD patients with cognitive deficits. The most differentiated results were found in the theta frequency band, frontal theta responses were the lowest in PD patients with dementia especially during the visual paradigm rather than the auditory paradigm. Conclusions Comprehensive analysis of Event-related oscillatory dynamics could successfully differentiate the cognitive decline in Parkinson’s disease patients. The differentiation between subject groups did not just appear in local circuits, but long distance connections were also impaired in PD patients with cognitive decline. Acknowledgments This work (Grant No. 214S111 ) was supported by TUBITAK .

Automatic Evaluation of Internal Combustion Engine Noise Based on an Auditory Model

To improve the accuracy and efficiency of the objective evaluation of noise quality from internal combustion engines, an automatic noise quality classification model was constructed by introducing an auditory model‐based acoustic spectrum analysis method and a convolutional neural network (CNN) model. A band‐pass filter was also designed in the model to automatically extract the features of the noise samples, which were later used as input data. The adaptive moment estimation (Adam) algorithm was used to optimize the weights of each layer in the network, and the model was used to evaluate sound quality. To evaluate the predictive performance of the CNN model based on the auditory input, a back propagation (BP) sound quality evaluation model based on psychoacoustic parameters was constructed and used as a control. When processing the label values of the samples, the correlation between the psychoacoustic parameters of the objective evaluation and evaluation scores was analyzed. Four psychoacoustic parameters with the greatest correlation with subjective evaluation results were selected as the input values of the BP model. The results showed that the sound quality evaluation model based on the CNN could predict the sound quality of internal combustion engines more accurately, and the input evaluation score based on the auditory spectrum in the CNN classification model was more accurate than the short‐time average energy input evaluation score based on the time domain.

Auditory Neuropathy and Spectrum of Disorder !$£ from a Audiological Perspective- A Rare Case Series

Auditory Neuropathy and Spectrum of Disorder !$£ from a Audiological Perspective- A Rare Case Series

Methylmercury Exposure Reduces the Auditory Brainstem Response of Zebra Finches (Taeniopygia guttata ).

Mercury contamination from mining and fossil fuel combustion causes damage to humans and animals worldwide. Mercury exposure has been implicated in mammalian hearing impairment, but its effect on avian hearing is unknown. In this study, we examined whether lifetime dietary mercury exposure affected hearing in domestic zebra finches (Taeniopygia guttata) by studying their auditory brainstem responses (ABRs). Zebra finches exposed to mercury exhibited elevated hearing thresholds, decreased amplitudes, and longer latencies in the ABR, the first evidence of mercury-induced hearing impairment in birds. Birds are a more appropriate model for the human auditory spectrum than most mammals because of similarities in frequency discrimination, vocal learning, and communication behavior. When mercury is considered in combination with other anthropogenic stressors such as noise pollution and habitat alteration, the hearing impairments we document here could substantially degrade avian auditory communication in wild birds.

Satellite speech quality measurement model based on a combination of auditory envelope feature and link loss

This paper focuses on Speech Quality Measurement for a satellite mobile communication system. In contrast to ground mobile communication systems, satellite speech quality measurement suffers from obvious jitter of long delays and severe satellite link losses. Auditory feature sensation and link loss measurement are most popular speech quality measurement models. However, long delay would cause the auditory feature sensation model with spreading of power spectrum, which furtherly diffuses the auditory spectrums to prevent human from hear correct responses. Nevertheless, measured error of link loss measurement would be enlarged gradually during the process of voice services. Therefore, a new speech quality measurement model based on the combination of auditory feature extraction from voice signal envelope and link loss from channel distortion is proposed. We analyze signal temporal envelope features and make power spectrum into auditory feature spectrum. The jitter of long delay and link loss are modeled as parameters to modify and compensate for the auditory feature spectrum, which also reduce the measurement distortion from transmission Doppler frequency offset to voice tone in satellite channel. A more understandable sensation estimation scores is proposed to present speech quality scores. The experimental results reveal that the new model reduces evaluation RMSE by 9.8% and is suited to the satellite mobile communications environment.

Distortion product otoacoustic emissions in geriatric dogs

Recordings of distortion product otoacoustic emissions (DPOAE) were taken from 28 geriatric dogs aged 12.2 ± 2.2 years and 15 control dogs aged 5.9 ± 3.0 years (mean ± standard deviation) to demonstrate frequency-specific changes in cochlear responses. Recordings were performed for primary frequencies of 2–12 kHz in 2 kHz increments. Brainstem auditory evoked response (BAER) recordings were also made from geriatric dogs for comparison with DPOAE responses. Significant decreases in DPOAE response amplitudes were observed at frequencies of 6–12 kHz in geriatric dogs compared to control dogs, reflecting loss of cochlear outer hair cells along the length of the cochlea. Significant decreases in response amplitudes were not seen at frequencies of 2 or 4 kHz. Decreases in BAER response amplitudes subjectively paralleled the depressed DPOAE amplitudes. No significant linear regression relationships were found for DPOAE response amplitude vs. age despite the progressive nature of age-related hearing loss. The reductions in response at all frequencies starting at the age where dogs are considered geriatric indicate that age-related hearing loss begins earlier in the life span. DPOAE recordings provide a means to assess cochlear function across different portions of the auditory spectrum for assessing hearing loss associated with aging, and potentially for losses from other causes of decreased auditory function.

Automatic Voice Pathology Detection With Running Speech by Using Estimation of Auditory Spectrum and Cepstral Coefficients Based on the All-Pole Model

Automatic voice pathology detection using sustained vowels has been widely explored. Because of the stationary nature of the speech waveform, pathology detection with a sustained vowel is a comparatively easier task than that using a running speech. Some disorder detection systems with running speech have also been developed, although most of them are based on a voice activity detection (VAD), that is, itself a challenging task. Pathology detection with running speech needs more investigation, and systems with good accuracy (ACC) are required. Furthermore, pathology classification systems with running speech have not received any attention from the research community. In this article, automatic pathology detection and classification systems are developed using text-dependent running speech without adding a VAD module. A set of three psychophysics conditions of hearing (critical band spectral estimation, equal loudness hearing curve, and the intensity loudness power law of hearing) is used to estimate the auditory spectrum. The auditory spectrum and all-pole models of the auditory spectrums are computed and analyzed and used in a Gaussian mixture model for an automatic decision. In the experiments using the Massachusetts Eye & Ear Infirmary database, an ACC of 99.56% is obtained for pathology detection, and an ACC of 93.33% is obtained for the pathology classification system. The results of the proposed systems outperform the existing running-speech-based systems. The developed system can effectively be used in voice pathology detection and classification systems, and the proposed features can visually differentiate between normal and pathological samples.