Gammatone Research Articles

Fault diagnosis of driving gear in battery swapping system based on auditory bionics

Rack and pinion drives (RPD) are widely used in battery swapping system (BSS) for electric heavy trucks (EHT), and due to the continuous heavy-load and high-intensity operation, along with the electric erosion, the gears in the RPD are always damaged, which causes unexpected consequences such as downtime or safety incidents. The working conditions of the RPD in BSS include uncertain noises, fluctuant and low speed, which pose steep challenges to accurate fault diagnosis. Considering the auditory resistance of interference, the low-frequency sensitivity of auditory perception, and the auditory saliency mechanism, to leverage the advantages of auditory perceptual mechanism in addressing the above challenges, as the contribution in artificial intelligence, we propose an entire vibration signal processing scheme based on auditory bionics, including some mathematical models for auditory mechanisms. For the application in engineering, the proposed scheme is employed for fault diagnosis of RPD in BSS in unique working conditions. First, adaptive resampling is used to smooth the speed fluctuation, then, Gammatone filters are employed to transform vibration signals to cochleograms, after that, based on auditory stream segregation and selective attention mechanisms, effective frequency channels and salient features are extracted from the cochleograms, besides, to improve the diagnosis accuracy, binaural features are also extracted, finally, based on (sectional) sparse representation and fusion, fault diagnosis is achieved. The effectiveness of the fault diagnosis scheme is demonstrated using a BSS prototype system.

Delayed-X harmonic synthesizer cancelling narrow bandpass noises by control signals via aural cartilage conduction

When a transducer is put on an aural cartilage, the transmitted vibration generates sound in the external auditory canal (i.e., cartilage conduction). A hearing device based on the cartilage conduction does not need occluding the external auditory canal. When an active noise control can adapt only to unwanted noise, the device enables natural conversations with unprocessed voice in the noisy environment (selective cancelation). To accomplish the selective cancelation, we proposed delayed-X harmonics synthesizer (DXHS) algorithm to minimize the damage for the speech quality. A target noise in this study was bandpass noise through a gammatone filter (center frequency: 500 Hz) overlapping the speech spectrum. After tracing the spectral envelope of the noise by using linear predictive coding (LPC), the DXHS outputted five pure tones distributed around the peak of envelope, and each step size parameter was adjusted according to the amplitude of the envelope. As results, our proposed method showed the noise reduction of 11.3 dB maintaining the speech quality in the computer simulations. During the adaptation, the step size adjustment enabled round off the spectral peak of the bandpass noise to avoid sharpening it.

Prediction of Operational Noise Uncertainty in Automotive Micro-Motors Based on Multi-Branch Channel–Spatial Adaptive Weighting Strategy

The acoustic performance of automotive micro-motors directly impacts the comfort and driving experience of both drivers and passengers. However, various motor production and testing uncertainties can lead to noise fluctuations during operation. Thus, predicting the operational noise range of motors on the production line in advance becomes crucial for timely adjustments to production parameters and process optimization. This paper introduces a prediction model based on a Multi-Branch Channel–Spatial Adaptive Weighting Strategy (MCSAWS). The model includes a multi-branch feature extraction (MFE) network and a channel–spatial attention module (CSAM). It uses the vibration and noise data from micro-motors’ idle operations on the production line as input to efficiently predict the operational noise uncertainty interval of automotive micro-motors. The model employs the VAE-GAN approach for data augmentation (DA) and uses Gammatone filters to emphasize the noise at the commutation frequency of the motor. The model was compared with Convolutional Neural Networks (CNNs) and Multilayer Perceptrons (MLPs). Experimental results demonstrate that the MCSAWS method is superior to conventional methods in prediction accuracy and reliability, confirming the feasibility of the proposed approach. This research can help control noise uncertainty in micro-motors’ production and manufacturing processes in advance.

A multi-level power grid enhanced identity authentication data management platform based on filtering algorithms

In response to the optimal extraction of DCT coefficients in facial images, the author proposes a DCT coefficient extraction method based on discriminant analysis. Based on the discriminant analysis of DCT coefficients, the DCT coefficients with high discriminant values are selected as features. Comparing the DPA based discrete cosine coefficient selection method proposed by the author with the traditional Zigzag discrete cosine coefficient selection method, experiments were conducted on the ORL face database and the Yale face database, respectively. The recognition performance on the ORL face database was higher than that on the Yale face database, as the facial image expression and lighting changes in the ORL database were relatively few, making it suitable for extracting key features. In response to the problem that the speech parameter MFCC is greatly affected by noise and can only reflect the static characteristics of speech, the author extracted gamma pass filtering cepstrum coefficients with human auditory characteristics and gamma pass sliding differential cepstrum coefficients that can reflect the dynamic characteristics of speech based on gamma tone filters and sliding differential cepstrum. In the NUST603 speech database, under pure background, the recognition rate based on GFSDCC features reached 89.88%, and the recognition effect based on GFCC features was 87.52%, which is 4.66% and 2.36% higher than that based on MFCC features. In noisy environments, the average recognition rates of speaker recognition systems based on GFCC and GFSDCC are 56.06% and 59.07%, while the average recognition rates of speaker recognition systems based on MFCC speech features are 53.89%, 2.17% and 5.18% higher, respectively. The gain in this recognition effect comes from the characteristics of the auditory model, as the Gammatone filter effectively reflects the noise resistance of the human auditory system.

Auditory-inspired adaptive frequency tracking

One of the best frequency trackers to date is the human (mammalian) auditory system, which has evolved through millions of years of resolving classification problems. It is a versatile, elegant and powerful sound processing unit. It excels in detecting, estimating, and classifying multiple targets simultaneously even in noisy environments. Hence, mimicking even some features of the auditory system could be beneficial in developing superior frequency tracking and classification algorithms. An auditory inspired adaptive synchrony capture filterbank (SCFB) signal processing architecture for tracking signal frequency components was proposed in a related paper [JASA-2013]. The SCFB architecture consists of a fixed array of traditional, passive linear, gammatone filters in cascade with a bank of three adaptively tunable bandpass filters that form a frequency-discriminator-loop (FDL). The SCFB exhibits many desirable properties for processing speech, music, and other complex sounds. In recent work [Dec2021], the algorithm was modified using adaptive tuning parameters, and a generalized way to determine/suppress voiced and unvoiced (silent) regions. This modified algorithm estimates frequencies with higher accuracy even in the presence of closely spaced input tones. Preliminary analysis with synthetic, human speech and humpback/whale-call signals demonstrates that the revised algorithm performs well. This talk will focus on follow-on work.

Investigating the Performance of Gammatone Filters and Their Applicability to Design Cochlear Implant Processing System

Commercially available cochlear implants are designed to aid profoundly deaf people in understanding speech and environmental sounds. A typical cochlear implant uses a bank of bandpass filters to decompose an audio signal into a set of dynamic signals. These filters’ critical center frequencies f0 imitate the human cochlea’s vibration patterns caused by audio signals. Gammatone filters (GTFs), with two unique characteristics: (a) an appropriate “pseudo resonant” frequency transfer function, mimicking the human cochlea, and (b) realizing efficient hardware implementation, could demonstrate them as unique candidates for cochlear implant design. Although GTFs have recently attracted considerable attention from researchers, a comprehensive exposition of GTFs is still absent in the literature. This paper starts by enumerating the impulse response of GTFs. Then, the magnitude spectrum, |H(f)|, and bandwidth, more specifically, the equivalent rectangular bandwidth (ERB) of GTFs, are derived. The simulation results suggested that optimally chosen filter parameters, e.g., critical center frequencies,f0; temporal decay parameter, b; and order of the filter, n, can minimize the interference of the filter bank frequencies and very likely model the filter bandwidth (ERB), independent of f0b. Finally, these optimized filters are applied to delineate a filter bank for a cochlear implant design based on the Clarion processor model.

Utilizing gammatone filter coefficient to improve human mouth-click signal detection using a multi-phase correlation process

This study introduces an enhanced structured signal processing scheme for detecting the “transmit-echo” of mouth-click signals used by blind individuals for echolocation. The processing scheme is based on coexisting work on the detection of the mouth-click signal, with an additional band-pass filter process introduced before synthesis, multi-phase correlation, and summation. The level of side lobes at the output was improved by more than −19 dB, and the number of local maxima was minimized by using a band-pass filter. The detection of “transmit-echo” results using artificial mouth-click signal data was validated and achieved a 100% success rate in detecting obstacles at 60 cm, 80 cm, and 100 cm. Nonetheless, the detection scheme discussed in this investigation is thought to be intuitive, having been learned from the human hearing process. The emerging concepts in this research are expected to benefit radar and sonar system applications in the near future.

Exploring Filter Banks and Spike Interval Statistics of Level-Crossing ADCs for Fault Diagnosis of Rolling Element Bearings

Nowadays, lots of data are generated in industries using vibration sensors to evaluate the equipment’s working condition and identify faults. A significant challenge is that only a small fraction of data can be transmitted for intelligent fault diagnosis and storage. The edge processing capacity is often insufficient for advanced analysis due to time and resource constraints. The neuromorphic signal encoding scheme efficiently reduces the data rate by encoding relevant signal changes into spike trains while discarding redundant information and noise, enabling energy-efficient neuromorphic processing. Due to the presence of dominant operational features and noise in the original measurements, signal pre-processing is required to extract the relevant features before spike coding and processing. The work investigates the effects of different filter banks (pre-processing methods) on the spike encodings for vibration measurements from bearings. This also includes bearing fault features diagnosis based on statistical analysis of generated spikes. The comparative analysis is made for benchmarking different signal pre-processing methods (e.g., envelope, empirical mode decomposition (EMD), and gammatone filter) on bearing vibration datasets. An event-triggered scheme, i.e., Level-crossing analog-to-digital converters (LC-ADCs) is applied to encode the vibration measurement to spikes. Inter-spike intervals (ISIs) statistics are analysed for fault diagnosis of bearings. The results obtained for CWRU bearing databases indicate a possible fault detection and diagnosis with significant data rate reduction and an opportunity for improved computational efficiency. With the developed approach, the envelope filter is found to be the most efficient of all. This work enables a new approach to improve the energy efficiency of condition monitoring systems and further sets a new course of research development in this area using neuromorphic technologies.

Human activities classification based on ϕ-OTDR system by utilizing gammatone filter cepstrum coefficient envelope using support vector machine

Human activities classification based on ϕ-OTDR system by utilizing gammatone filter cepstrum coefficient envelope using support vector machine

Detection method for electric impact drill parts defect based on auditory peripheral model

The accurate non-contact detection for electric impact drill parts defect can significantly improve the production efficiency. In this paper, an acoustic-based method is proposed to detect parts defect by mimicking the physiological auditory perceptual principles. The method firstly combined Gammatone filter banks and Meddis model to simulate cochlear processing mechanism to calculate the time–frequency information of the electric impact drill working acoustic signal. Then the subband energy-entropy differential ratio was described to extract the time–frequency features. Based on the optimized features by the principal component analysis, the parts defect detection was achieved by the support vector machine. The results with collected electric impact drill acoustic data show that the detection accuracy by this method can reach 97.8 %, which is 5.12 % higher than the Mel frequency cepstral coefficient method and 7.56 % higher than the time–frequency domain feature method. The proposed method can provide a new idea for non-contact part defect detection of electric impact drill in factories.

End-to-End Speaker Profiling Using 1D CNN Architectures and Filter Bank Initialization

The automatic estimation of speaker characteristics, such as height, age, and gender, has various applications in forensics, surveillance, customer service, and many human-robot interaction applications. These applications are often required to produce a response promptly. This work proposes a novel approach to speaker profiling by combining filter bank initializations, such as continuous wavelets and gammatone filter banks, with one-dimensional (1D) convolutional neural networks (CNN) and residual blocks. The proposed end-to-end model goes from the raw waveform to an estimated height, age, and gender of the speaker by learning speaker representation directly from the audio signal without relying on handcrafted and pre-computed acoustic features. The conducted experiments on the TIMIT dataset show that the proposed approach outperforms many previous studies on speaker profiling with a mean absolute error (MAE) of 5.18 and 4.91 cm in height estimation and MAE of 5.36 and 6.07 years in age estimation for males and females, respectively, and achieving an accuracy of 99.98% in gender prediction.

Bayesian optimized GoogLeNet based respiratory signal prediction model from empirically decomposed gammatone visualization

Discrimination of normal and adventitious respiratory sounds from stethoscope auscultation by human ears is challenging owing to low frequency characteristics and varying frequency range for inspiration and expiration. This makes the diagnosis of pulmonary disorders a subjective one relying on the experience and hearing capability of the physician. Most computer assisted diagnosis systems formulated to address these limitations fail to capture the inherent acoustic property of respiratory sounds close to human auditory system. To circumvent this problem, this study exploits the gammatone filter banks to evaluate the distribution of all frequency components present in the signal. To categorize the respiratory signals, GoogLeNet based Convolutional Neural Networks (CNN) prediction model is developed through Time-Frequency (TF) visualization of gammatone cepstral coefficients acquired from decomposed Intrinsic Mode Functions (IMFs) in an empirical manner. As the performance of the CNN model is greatly dependent on the learning environment, this study also tends to optimize the values of the hyper parameters to enhance the classification performance of the CNN model. Accordingly, the optimal values of initial learning rate, L2 regularization and momentum are identified for both Stochastic Gradient Descent Momentum (SGDM) and Adaptive Momentum (ADAM) optimizer using Bayesian optimization technique. Experimentation is carried out for three TF visualization methods viz. spectrograms, scalograms and Constant Q spectrograms. Evaluated results show that scalogram method of classification yields high accuracy of 87.37% and 88.32% for default selection of hyperparameters using SGDM and ADAM optimizers and with optimal selection of hyperparameters based on objective function reveal an improved accuracy of 93.68 % and 95.67% for SGDM and ADAM optimizers.

Fault diagnosis of plunger pump based on audio signal combined with meta-transfer learning

To solve the problems of insufficient samples and weak fault features of audio signals in the fault diagnosis of plunger pump, this paper proposes a fault diagnosis method of plunger pump based on audio signal combined with meta-transfer learning (MTL-PAFD). The method takes the audio signals of the plunger pump as samples, which are acquired by a single sensor. Through the Gammatone filter bank processing, the representation ability of the audio signal under strong noise interference is effectively improved. Then combined with meta-transfer learning, the few-shot fault diagnosis of plunger pump is realized. In addition, according to the actual needs of fault diagnosis of plunger pump, the test method of meta-transfer learning in fault diagnosis application is improved, which can process unknown fault classes adaptively. Experimental results show that MTL-PAFD has a fault diagnosis accuracy of 91.41% for seen classes. After fast adaptive learning, it can achieve an accuracy of 89.64% when identifying unseen fault classes.

Adaptive Information Hiding Method Based on Feature Extraction for Visible Light Communication

Visible Light Communication (VLC) is an emerging short-range optical communication technology that can alleviate spectrum congestion. However, VLC faces security problems with man-in-the-middle hijacking and bypass listening. Since the covert transmission of visible light information has the characteristics of strong concealment and difficult detection, VLC based on information hiding becomes a new paradigm to solve these security problems. This paper presents a method in which Red, Green, Blue (RGB) Light-emitting Diode (LED) is used to secure the VLC by using the information hiding technique. Specifically, a gammatone filter bank-based feature extraction method is suggested. This method extracts robust vector for information hiding and extraction. To hide and extract the information, a dither modulation information hiding scheme based on the adaptive optimization is proposed. The presented method uses dither modulation to hide information in the extracted feature vector, which can effectively improve the success rate of information extraction. On the basis of performance analysis, the superiority of the presented method is illustrated by comparing with the existing methods.

Wavelet-Based Weighted Low-Rank Sparse Decomposition Model for Speech Enhancement Using Gammatone Filter Bank Under Low SNR Conditions

Estimating noise-related parameters in unsupervised speech enhancement (SE) techniques is challenging in low SNR and non-stationary noise environments. In the recent SE approaches, the best results are achieved by partitioning noisy speech spectrograms into low-rank noise and sparse speech parts. However, a few limitations reduce the performance of these SE methods due to the use of overlap and add in STFT process, noisy phase, due to inaccurate estimation of low rank in nuclear norm minimization and Euclidian distance measure in the cost function. These aspects can cause a loss of information in the reconstructed signal when compared to clean speech. To solve this, we propose a novel wavelet-based weighted low-rank sparse decomposition model for enhancing speech by incorporating a gammatone filter bank and Kullback–Leibler divergence. The proposed framework differs from other strategies in which the SE is carried entirely in time domain without the need for noise estimation. Further, to reduce the word error rate, these algorithms were trained and tested on a typical automatic speech recognition module. The experimental findings indicate that the proposed cascaded model has shown significant improvement under low SNR conditions over individual and traditional methods with regard to SDR, PESQ, STOI, SIG, BAK and OVL.

Auditory-inspired adaptive frequency tracking

One of the best frequency trackers to date is the human (mammalian) auditory system, which has evolved through millions of years of resolving classification problems. It is a versatile, elegant and powerful sound processing unit. It excels in detecting, estimating, and classifying multiple targets simultaneously even in noisy environments. Hence, mimicking even some features of the auditory system could be beneficial in developing superior frequency tracking and classification algorithms. An auditory inspired adaptive synchrony capture filterbank (SCFB) signal processing architecture for tracking signal frequency components was proposed in a related paper [JASA (2013)]. The SCFB architecture consists of a fixed array of traditional, passive linear, gammatone filters in cascade with a bank of three adaptively tunable bandpass filters that form a frequency-discriminator-loop (FDL). The SCFB exhibits many desirable properties for processing speech, music, and other complex sounds. In recent work (Dec 2021), the algorithm was modified using adaptive tuning parameters, and a generalized way to determine/suppress voiced and unvoiced (silent) regions. This modified algorithm estimates frequencies with higher accuracy even in the presence of closely spaced input tones. Preliminary analysis with synthetic, human speech and humpback/whale-call signals demonstrates that the revised algorithm performs well. This talk will focus on the latest updates.

Bispectral feature speech intelligibility assessment metric based on auditory model

A bispectral feature based predictive speech intelligibility metric (GMBSIM) using a more refined functional auditory model of ear is proposed. In the auditory model of ear, Gammatone filter banks and Meddis inner hair cell auditory model is combined to simulate the ear function. With input speech signal divided into 32 auditory subbands, and each subband signal passed through the inner hair cell model, the bispectrum of each subband signal in time domain is estimated by frames. And then bispectral features are extracted and chosen to calculate the speech intelligibility. The proposed GMBSIM has relative low computational complexity by omitting the spectrogram or neurogram image transformation. Considering the ear's perception and processing of speech signals makes the metric is advantageous to the classical metrics. And the last but not the least, the proposed GMBSIM metric is verified favorably across a range of conditions spanning reverberation, additive noise, and distortion such as jitter, which means it can be applied in most kinds of complex background noise environment.

Alpha and Low Gamma Embedded With White Noise Binaural Beats Modulating Working Memory among Malaysian Young Adult: A Preliminary fMRI Study

Introduction: Binaural beats (BB) provisions alpha and gamma have been suggested to modulate working memory (WM), while white noise (WN) acted as a control condition. Methods: The current study overlays WN on alpha and gamma tones to study its modulating role on WM performance. A block-design n-back task paradigm used to determine the effect of load on embedded BB on WM performance using functional magnetic resonance imaging. Results: Six young adults (3 males and 3 females) with mean age of 23.5 ± 0.84 within the Kota Bharu vicinity participated in the study. A repeated-measures ANOVA (p<0.05) on response accuracy indicate medium effect size on condition (η2 =0.420), and large effect sizes on groups (η2 = 0.388) and load (η2 = 0.487). The potential practical difference is more evident on low- (0-back) and high-load (3-back). GWN provision marginally excels, implying its entrainment may benefit WM processing. A repeated-measures ANOVA (p<0.05) on reaction time (RT) implied a large effect size on all variables (condition: η2=0.065, groups: η2=0.227 and load: η2=0.169). It was observed that BB exposure elicits a slow processing speed which worsens RT. The neural correlates suggest activated regions in GWN and AWN are associated with attentional mechanisms and WM processes. Conclusion: Preliminary findings indicate both embedded BB has a potential to improve WM performance with the cost of slower processing speed. GWN provision modulates attentional mechanisms benefiting WM performance and AWN may enhance performance in extreme ends of WM load.

Speech Separation Algorithm Using Gated Recurrent Network Based on Microphone Array

Speech separation is an active research topic that plays an important role in numerous applications, such as speaker recognition, hearing prosthesis, and autonomous robots. Many algorithms have been put forward to improve separation performance. However, speech separation in reverberant noisy environment is still a challenging task. To address this, a novel speech separation algorithm using gate recurrent unit (GRU) network based on microphone array has been proposed in this paper. The main aim of the proposed algorithm is to improve the separation performance and reduce the computational cost. The proposed algorithm extracts the sub-band steered response power-phase transform (SRP-PHAT) weighted by gammatone filter as the speech separation feature due to its discriminative and robust spatial position information. Since the GRU network has the advantage of processing time series data with faster training speed and fewer training parameters, the GRU model is adopted to process the separation features of several sequential frames in the same sub-band to estimate the ideal Ratio Masking (IRM). The proposed algorithm decomposes the mixture signals into time-frequency (TF) units using gammatone filter bank in the frequency domain, and the target speech is reconstructed in the frequency domain by masking the mixture signal according to the estimated IRM. The operations of decomposing the mixture signal and reconstructing the target signal are completed in the frequency domain which can reduce the total computational cost. Experimental results demonstrate that the proposed algorithm realizes omnidirectional speech separation in noisy and reverberant environments, provides good performance in terms of speech quality and intelligibility, and has the generalization capacity to reverberate.

Sound Events Localization and Detection Using Bio-Inspired Gammatone Filters and Temporal Convolutional Neural Networks

The auditory brain circuits are biologically constructed to recognize and localize sounds by encoding a combination of cues that help individuals interpret sounds. The development of computational methods inspired by human capacities has established opportunities for improving machine hearing. Recent studies based on deep learning show that using convolutional recurrent neural networks (CRNNs) is a promising approach for sound event detection and localization in spatial sound. Nevertheless, depending on the sound environment, the performance of these systems is still far from reaching perfect metrics. Therefore, this work intends to boost the performance of state-of-the-art (SOTA) systems by using bio-inspired gammatone auditory filters and intensity vectors (IVs) for the acoustic feature extraction stage, along with the implementation of a temporal convolutional network (TCN) block into a CRNN model, to capture long term dependencies. Three data augmentation techniques are applied to increase the small number of samples in spatial audio datasets. The mentioned stages constitute our proposed Gammatone-based Sound Events Localization and Detection (G-SELD) system, which exceeded the SOTA results on four spatial audio datasets with different levels of acoustical complexity and with up to three sound sources overlapping in time.