Gammatone Cepstral Coefficients Research Articles

Fault diagnosis of driving gear in a battery swapping system based on audio features and SRC-Adaboost

Abstract Because of electrification conditions, key components of battery swapping systems (BSSs) for electric heavy trucks are always damaged by electric erosion, which presents challenges to the safety and efficiency of high-intensity transportation. Due to the special working conditions of a BSS, the fault diagnosis of its driving gear encounters several issues, including reciprocation motion, low and fluctuating speed, and complicated noises. To solve these problems, audio features, including Mel-frequency cepstral coefficients and Gammatone cepstral coefficients, are extracted from the vibration signals. Then, these features are utilized to construct an original dictionary. Next, based on data augmentation and dictionary learning, a robust dictionary is generated from the original dictionary. Finally, with the robust dictionary, sparse representation-based classification is integrated into AdaBoost to achieve accurate fault diagnosis for the driving gear in BSS. The effectiveness of the fault diagnosis scheme is validated based on the monitoring data of the BSS, and the accuracy of fault diagnosis is 99.17%.

Data augmentation and hybrid feature amalgamation to detect audio deep fake attacks

The ability to distinguish between authentic and fake audio is become increasingly difficult due to the increasing accuracy of text-to-speech models, posing a serious threat to speaker verification systems. Furthermore, audio deepfakes are becoming a more likely source of deception with the development of sophisticated methods for producing synthetic voice. The ASVspoof dataset has recently been used extensively in research on the detection of audio deep fakes, together with a variety of machine and deep learning methods. The proposed work in this paper combines data augmentation techniques with hybrid feature extraction method at front-end. Two variants of audio augmentation method and Synthetic Minority Over Sampling Technique (SMOTE) have been used, which have been combined individually with Mel Frequency Cepstral Coefficients (MFCC), Gammatone Cepstral Coefficients (GTCC) and hybrid these two feature extraction methods for implementing front-end feature extraction. To implement the back-end our proposed work two deep learning models, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), and two Machine Learning (ML) classifier Random Forest (RF) and Support Vector Machine (SVM) have been used. For training, and evaluation ASVspoof 2019 Logical Access (LA) partition, and for testing of the said systems, and ASVspoof 2021 deep fake partition have been used. After analysing the results, it can be observed that combination of MFCC+GTCC with SMOTE at front-end and LSTM at back-end has outperformed all other models with 99% test accuracy, and 1.6 % Equal Error Rate (EER) over deepfake partition. Also, the testing of this best combination has been done on DEepfake CROss-lingual (DECRO) dataset. To access the effectiveness of proposed model under noisy scenarios, we have analysed our best model under noisy condition by adding Babble Noise, Street Noise and Car Noise to test data.

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.

CNN AND LSTM FOR THE CLASSIFICATION OF PARKINSON'S DISEASE BASED ON THE GTCC AND MFCC

Parkinson's disease is a recognizable clinical syndrome with a variety of causes and clinical presentations; it represents a rapidly growing neurodegenerative disorder. Since about 90 percent of Parkinson's disease sufferers have some form of early speech impairment, recent studies on tele diagnosis of Parkinson's disease have focused on the recognition of voice impairments from vowel phonations or the subjects' discourse. In this paper, we present a new approach for Parkinson's disease detection from speech sounds that are based on CNN and LSTM and uses two categories of characteristics Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) obtained from noise-removed speech signals with comparative EMD-DWT and DWT-EMD analysis. The proposed model is divided into three stages. In the first step, noise is removed from the signals using the EMD-DWT and DWT-EMD methods. In the second step, the GTCC and MFCC are extracted from the enhanced audio signals. The classification process is carried out in the third step by feeding these features into the LSTM and CNN models, which are designed to define sequential information from the extracted features. The experiments are performed using PC-GITA and Sakar datasets and 10-fold cross validation method, the highest classification accuracy for the Sakar dataset reached 100% for both EMD-DWT-GTCC-CNN and DWT-EMD-GTCC-CNN, and for the PC-GITA dataset, the accuracy is reached 100% for EMD-DWT-GTCC-CNN and 96.55% for DWT-EMD-GTCC-CNN. The results of this study indicate that the characteristics of GTCC are more appropriate and accurate for the assessment of PD than MFCC.

A late fusion deep neural network for robust speaker identification using raw waveforms and gammatone cepstral coefficients

Speaker identification aims at determining the speaker identity by analyzing his voice characteristics, and relies typically on statistical models or machine learning techniques. Frequency-domain features are by far the most used choice to encode the audio input in sound recognition. Recently, some studies have also analyzed the use of time-domain raw waveform (RW) with deep neural network (DNN) architectures. In this paper, we hypothesize that both time-domain and frequency-domain features can be used to increase the robustness of speaker identification task in adverse noisy and reverberation conditions, and we present a method based on a late fusion DNN using RWs and gammatone cepstral coefficients (GTCCs). We analyze the characteristics of RW and spectrum-based short-time features, reporting advantages and limitations, and we show that the joint use can increase the identification accuracy. The proposed late fusion DNN model consists of two independent DNN branches made primarily by convolutional neural networks (CNN) and fully connected neural networks (NN) layers. The two DNN branches have as input short-time RW audio fragments and GTCCs, respectively. The late fusion is computed on the predicted scores of the DNN branches. Since the method is based on short segments, it has the advantage of being independent from the size of the input audio signal, and the identification task can be computed by summing the predicted scores over several short-time frames. Analysis of speaker identification performance computed with simulations show that the late fusion DNN model improves the accuracy rate in adverse noise and reverberation conditions in comparison to the RW, the GTCC, and the mel-frequency cepstral coefficients (MFCCs) features. Experiments with real-world speech datasets confirm the efficiency of the proposed method, especially with small-size audio samples.

Speech phoneme and spectral smearing based non-invasive COVID-19 detection.

COVID-19 is a deadly viral infection that mainly affects the nasopharyngeal and oropharyngeal cavities before the lung in the human body. Early detection followed by immediate treatment can potentially reduce lung invasion and decrease fatality. Recently, several COVID-19 detections methods have been proposed using cough and breath sounds. However, very little study has been done on the use of phoneme analysis and the smearing of the audio signal in COVID-19 detection. In this paper, this problem has been addressed and the classification of speech samples has been carried out in COVID-19-positive and healthy audio samples. Additionally, the grouping of the phonemes based on reference classification accuracies have been proposed for effectiveness and faster detection of the disease at a primary stage. The Mel and Gammatone Cepstral coefficients and their derivatives are used as the features for five standard machine learning-based classifiers. It is observed that the generalized additive model provides the highest accuracy of 97.22% for the phoneme grouping "/t//r//n//g//l/." This smearing-based phoneme classification technique can also be used in the future to classify other speech-related disease detections.

Comparative Analysis of Different Sampling Rates on Environmental Sound Classification Using the Urbansound8k Dataset

Environmental sound classification (ESC) has gained increasing attention in recent years. This study focuses on the evaluation of the popular public dataset Urbansound8k (Us8k) at different sampling rates using hand crafted features. The Us8k dataset contains environment sounds recorded at various sampling rates, and previous ESC works have uniformly resampled the dataset. Some previous work converted this data to different sampling rates for various reasons. Some of them chose to convert the rest of the dataset to 44,100, as the majority of the Us8k files were already at that sampling rate. On the other hand, some researchers down sampled the dataset to 8000, as it reduced computational complexity, while others resampled it to 16,000, aiming to achieve a balance between higher classification accuracy and lower computational complexity. In this research, we assessed the performance of ESC tasks using sampling rates of 8000 Hz, 16,000 Hz, and 44,100 Hz by extracting the hand crafted features Mel frequency cepstral coefficient (MFCC), gamma tone cepstral coefficients (GTCC), and Mel Spectrogram (MelSpec). The results indicated that there was no significant difference in the classification accuracy among the three tested sampling rates.

Replay Attack Detection in Automatic Speaker Verification Using Gammatone Cepstral Coefficients and ResNet-Based Model

This paper presents a method for detecting replay attacks in an automatic speaker verification system. The replay attack is of interest because it is the most straightforward, effective attack, and difficult to detect. Even though many speech features and classifiers have been proposed, the detection performance, such as an equal error rate (EER), accuracy, and balanced accuracy, need to be improved. Therefore, we propose a method for replay attack detection that applies the Gammatone cepstral coefficients with a ResNet-based model. The proposed method was evaluated and compared with existing methods and baselines in the ASVspoof 2019 challenge. The results indicated that the proposed method outperforms our previous method and the baselines in which the EER was 8.4%. In addition, the accuracy and balanced accuracy of the spoofing detection were improved.

Voice spoofing countermeasure for voice replay attacks using deep learning

In our everyday lives, we communicate with each other using several means and channels of communication, as communication is crucial in the lives of humans. Listening and speaking are the primary forms of communication. For listening and speaking, the human voice is indispensable. Voice communication is the simplest type of communication. The Automatic Speaker Verification (ASV) system verifies users with their voices. These systems are susceptible to voice spoofing attacks - logical and physical access attacks. Recently, there has been a notable development in the detection of these attacks. Attackers use enhanced gadgets to record users’ voices, replay them for the ASV system, and be granted access for harmful purposes. In this work, we propose a secure voice spoofing countermeasure to detect voice replay attacks. We enhanced the ASV system security by building a spoofing countermeasure dependent on the decomposed signals that consist of prominent information. We used two main features— the Gammatone Cepstral Coefficients and Mel-Frequency Cepstral Coefficients— for the audio representation. For the classification of the features, we used Bi-directional Long-Short Term Memory Network in the cloud, a deep learning classifier. We investigated numerous audio features and examined each feature’s capability to obtain the most vital details from the audio for it to be labelled genuine or a spoof speech. Furthermore, we use various machine learning algorithms to illustrate the superiority of our system compared to the traditional classifiers. The results of the experiments were classified according to the parameters of accuracy, precision rate, recall, F1-score, and Equal Error Rate (EER). The results were 97%, 100%, 90.19% and 94.84%, and 2.95%, respectively.

Satranç Oyunu için CNN Kullanılarak Türkçe Komutları Tanıma

A platform has been created that allows playing chess with Turkish voice commands. The aim of this study is to enable individuals with limited movement abilities as a result of congenital reasons or a certain disease or accident to play chess and perform a social activity without the help of another person, and to be rehabilitated at the same time. It consists of three parts: Chess module, Human-computer interaction module and Artificial Intelligence module. 29 words have been determined to provide movement in the game on the platform. Voice recordings from 151 people, 86 men and 65 women, were used. Feature selection was made on 43790 voice recordings by using mel frequency cepstral coefficients (MFCC) and gammatone cepstral coefficients (GTCC) methods. The results obtained were classified using the traditional CNN model. The data obtained after using MFCC and GTCC methods were used as inputs in the CNN model. In addition, the data obtained by the two methods were combined and trained in the model. Depending on the methods used in the created model, 83% to 85.9% results were obtained. It was determined that the results obtained using the MFCC method were more successful.

Toward Realigning Automatic Speaker Verification in the Era of COVID-19

The use of face masks has increased dramatically since the COVID-19 pandemic started in order to to curb the spread of the disease. Additionally, breakthrough infections caused by the Delta and Omicron variants have further increased the importance of wearing a face mask, even for vaccinated individuals. However, the use of face masks also induces attenuation in speech signals, and this change may impact speech processing technologies, e.g., automated speaker verification (ASV) and speech to text conversion. In this paper we examine Automatic Speaker Verification (ASV) systems against the speech samples in the presence of three different types of face mask: surgical, cloth, and filtered N95, and analyze the impact on acoustics and other factors. In addition, we explore the effect of different microphones, and distance from the microphone, and the impact of face masks when speakers use ASV systems in real-world scenarios. Our analysis shows a significant deterioration in performance when an ASV system encounters different face masks, microphones, and variable distance between the subject and microphone. To address this problem, this paper proposes a novel framework to overcome performance degradation in these scenarios by realigning the ASV system. The novelty of the proposed ASV framework is as follows: first, we propose a fused feature descriptor by concatenating the novel Ternary Deviated overlapping Patterns (TDoP), Mel Frequency Cepstral Coefficients (MFCC), and Gammatone Cepstral Coefficients (GTCC), which are used by both the ensemble learning-based ASV and anomaly detection system in the proposed ASV architecture. Second, this paper proposes an anomaly detection model for identifying vocal samples produced in the presence of face masks. Next, it presents a Peak Norm (PN) filter to approximate the signal of the speaker without a face mask in order to boost the accuracy of ASV systems. Finally, the features of filtered samples utilizing the PN filter and samples without face masks are passed to the proposed ASV to test for improved accuracy. The proposed ASV system achieved an accuracy of 0.99 and 0.92, respectively, on samples recorded without a face mask and with different face masks. Although the use of face masks affects the ASV system, the PN filtering solution overcomes this deficiency up to 4%. Similarly, when exposed to different microphones and distances, the PN approach enhanced system accuracy by up to 7% and 9%, respectively. The results demonstrate the effectiveness of the presented framework against an in-house prepared, diverse Multi Speaker Face Masks (MSFM) dataset, (IRB No. FY2021-83), consisting of samples of subjects taken with a variety of face masks and microphones, and from different distances.

Voice spoofing detector: A unified anti-spoofing framework

Voice controlled systems (VCS) in Internet of Things (IoT), speaker verification systems, voice-based biometrics, and other voice-assistant-enabled systems are vulnerable to different spoofing attacks i.e., replay, cloning, cloned-replay, etc. VCS are not only susceptible to these attacks in a non-network environment, but they are also vulnerable to multi-order spoofing attacks in networked IoT. Additionally, deepfakes with artificially generated audio pose a great threat to the all systems having voice-interfaces. Most of the existing countermeasures against these voice spoofing attacks work for only one specific attack (e.g. voice replay) and fail to generalize this for other classes of spoofing attacks. Additionally, generalization is also crucial for cross-corpora evaluation. Thus, there exists a need to develop a unified voice anti-spoofing framework capable of detecting multiple spoofing attacks. This work presents a unified anti-spoofing framework that uses novel (ATCoP-GTCC) features to combat the variety of voice spoofing attacks. The proposed novel acoustic-ternary co-occurrence patterns (ATCoP) encode the co-occurrence of similar patterns between the center and neighboring samples. Our experiments demonstrate that ATCoP can better capture the microphone induced distortions in replays, unnatural prosody and algorithmic artifacts in cloned samples, and both the distortions and artifacts in cloned-replays including compression on multi-hop attacks in the spoofing samples. The performance of ATCoP could be further enhanced by the Gammatone cepstral coefficients. To evaluate the effectiveness of the proposed anti-spoofing system for multi-order replay and cloned-replay attacks detection, we created a diverse voice spoofing detection corpus (VSDC) containing multi-order replay and cloned-replay audios against the bonafide and cloned audio recordings, respectively. Experimental results obtained on VSDC, ASVspoof 2019, Google’s LJ Speech, and YouTube deepfakes datasets illustrate the effectiveness of the proposed system in terms of accurate detection for a variety of voice spoofing attacks.

Comparative Analysis of Machine Learning Algorithms for Classification of Environmental Sounds and Fall Detection

In recent years, number of elderly people in population has been increased because of the rapid advancements in the medical field, which make it necessary to take care of old people. Accidental fall incidents are life-threatening and can lead to the death of a person if first aid is not given to the injured person. Immediate response and medical assistance are necessary in case of accidental fall incidents to elderly people. The research community explored various fall detection systems to early detect fall incidents, however, still there exist numerous limitations of the systems such as using expensive sensors, wearable sensors that are hard to wear all the time, camera violates the privacy of person, and computational complexity. In order to address the above-mentioned limitations of the existing systems, we proposed a novel set of integrated features that consist of melcepstral coefficients, gammatone cepstral coefficients, and spectral skewness. We employed a decision tree for the classification performance of both binary problems and multi-class problems. We obtained an accuracy of 91.39%, precision of 96.19%, recall of 91.81%, and F1-score of 93.95%. Moreover, we compared our method with existing state-of-the-art methods and the results of our method are higher than other methods. Experimental results demonstrate that our method is reliable for use in medical centers, nursing houses, old houses, and health care provisions.

음성신호를 이용한 양방향 LSTM 기반 우울증 진단

우울증은 개인의 전반적인 삶에 영향을 주고 감정, 생각, 신체 상태, 그리고 행동 등에 변화를 일으키는 심각한 정신질환이다. 따라서 우울증을 초기에 정확하게 진단하는 것이 중요하고 이를 위해 딥러닝을 이용한 여러 가지 시스템 개발되고 있다. 본 논문에서는 음성신호를 이용하여 Bi-LSTM(Bi-directional Long Short-Term Memory) 기반 우울증 진단을 위한 딥러닝 모델을 제안하고 성능을 비교하고 분석한다. 학습에는 딥러닝 모델 중 하나인 Bi-LSTM 모델을 사용했다. 음성신호의 특징은 MFCC(Mel-Frequency Cepstral Coefficient), GTCC(Gammatone Cepstral Coefficients)를 이용해 추출했고, 클래스 불균형을 해결하기 위해 데이터 확장을 수행했다. 데이터 확장 전 Bi-LSTM 모델의 성능은 약 56.58%였고, 확장 후의 성능은 약 98.49%로 학습데이터 확장을 통해 클래스 불균형 문제를 해결함으로써 모델의 분류 성능을 개선했다.

Voice Spoofing Countermeasure Based on Spectral Features to Detect Synthetic Attacks Through LSTM

With the growing number of voice-controlled devices, it is necessary to address the potential vulnerabilities of Automatic Speaker Verification (ASV) against voice spoofing attacks such as Physical Access (PA) and Logical Access (LA) attacks. To improve the reliability of ASV systems, researchers have developed various voice spoofing countermeasures. However, it is hard for the voice anti-spoofing systems to effectively detect the synthetic speech attacks that are generated through powerful spoofing algorithms and have quite different statistical distributions. More importantly, the speedy improvement of voice spoofing structures is producing the most effective attacks that make ASV structures greater vulnerable to stumble on those voice spoofing assaults. In this paper, we proposed a unique voice spoofing countermeasure which is successful to hit upon the LA attacks (i.e., artificial speech and transformed speech) and classify the spoofing structures by the usage of Long Short-Term Reminiscence (LSTM). The novel set of spectral features i.e., Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Cepstral Coefficients (GTCC), and spectral centroid are capable to seize maximum alterations present in the cloned audio. The proposed system achieved remarkable accuracy of 98.93%, precision of 100%, recall of 92.32%, F1-score of 96.01%, and an Equal Error Rate (EER) of 1.30%. Our method achieved 8.5% and 7.02% smaller EER than the baseline methods such as Constant-Q Cepstral Coefficients (CQCC) using Gaussian Mixture Model (GMM) and Linear Frequency Cepstral Coefficients (LFCC) using GMM, respectively. We evaluated the performance of the proposed system on the standard dataset i.e., ASVspoof2019 LA. Experimental results and comparative analysis with other existing state-of-the-art methods illustrate that our method is reliable and effective to be used for the detection of voice spoofing attacks.

Diagnosis of Depression Based on Four-Stream Model of Bi-LSTM and CNN From Audio and Text Information

Recent development trends in artificial intelligence applications have seen increasing interest in the design of automated systems for depression detection and diagnosis among the affective computing community. Particularly, active research has been conducted in depression diagnosis, based on multi-modal approaches in deep learning technology, which enable utilization of various information through fusion of varied data types. This study proposes a four-stream-based depression diagnosis model consisting of Bidirectional Long Short-Term Memory (Bi-LSTM) and convolutional neural networks (CNN), using speech and text data. One-dimensional features of audio signals are extracted using Mel Frequency Cepstral Coefficients and Gammatone Cepstral Coefficients, and two-dimensional features are extracted from Bark, equivalent rectangular bandwidth, and Log-Mel spectrograms, based on time-frequency transform. The extracted features are applied to Bi-LSTM and CNN-based transfer learning models. Word encoding was used for mapping of text to sequences with numeric indices, and word embedding used for representation of all words in numeric dense vectors. These were applied to Bi-LSTM and n-gram-based CNN models. Finally, an ensemble of the softmax values output from the four deep learning models was used to perform depression diagnosis, based on the proposed four-stream model. Using the proposed model, experiments were performed with the Extended Distress Analysis Interview Corpus Wizard of Oz depression database and other datasets. Experimental results showed improved performance by 10.7% to 11.9% over two-stream-based state-of-the-art methods. This demonstrates that the proposed model is effective for depression diagnosis.

Development of Optimal Feature Selection and Deep Learning Toward Hungry Stomach Detection Using Audio Signals

The process of transmitting signals to the body regarding the hungry stomach is referred to as the migrating motor complex (MMC) process. The intestines and stomach are considered for sensing the unavailability of food in the body. Hence, the receptors present in the stomach wall generate the electrical activity waves and activate the hunger. In general, audio signal processing algorithms include signal analysis, property extraction, and behavior prediction, identifying the pattern available in the signal, and predicting how a specific signal is correlated to various identical signals. The major challenge here is to consider the audio signals that are produced from the stomach for identifying the growling sound that well describes the hungry. The main intent of this paper is to develop an intelligent model using the deep learning concept for recognizing the hungry stomach by using the synthetically collected audio signals through mobile phones. This makes society reaching the hungry stomach by way of intelligent technology. The proposed detection model covers different phases for automated hungry stomach detection. The data acquisition is performed by gathering information using mobile phones. Further, the pre-processing of the signals is done by the median filtering and the smoothening methods. In order to perform the proper classification, the spectral features like spectral centroid, spectral roll-off, spectral skewness, spectral kurtosis, spectral slope, spectral crest factor, and spectral flux, and cepstral domain features like mel-frequency cepstral coefficients (MFCCs), linear prediction cepstral coefficients (LPCCs), Perceptual linear prediction (PLP) cepstral coefficients, Greenwood function cepstral coefficients (GFCC), and gammatone cepstral coefficients (GTCCs) are extracted. Further, the optimal feature selection is done by the improved meta-heuristic algorithm called best and worst position updated deer hunting optimization algorithm (BWP-DHOA). An improved deep learning model called optimized recurrent neural network (RNN) is used for classifying the optimal features of the audio signal into growling sound and burp sound. Finally, the performance comparison over the existing models proves the efficiency and reliability of the proposed model.

Turkish Voice Commands based Chess Game using Gammatone Cepstral Coefficients

Turkish Voice Commands based Chess Game using Gammatone Cepstral Coefficients

Unsupervised feature selection and NMF de-noising for robust Speech Emotion Recognition

Speech feature fusion is the most commonly used phenomenon for improving the accuracy in Speech Emotion Recognition (SER). But in this, there is a disadvantage of increasing the complexity in SER system in terms of processing time. Besides this, some of the features could be redundant and do not contribute for SER and lead to incorrect emotion prediction and reduction in SER accuracy. To overcome this problem, in this paper, unsupervised feature selection is applied to the feature set with the combination of INTERSPEECH 2010 paralinguistic features, Gammatone Cepstral Coefficients (GTCC) and Power Normalized Cepstral Coefficients (PNCC). The Feature Selection with Adaptive Structure Learning (FSASL), Unsupervised Feature Selection with Ordinal Locality (UFSOL) and a novel Subset Feature Selection (SuFS) algorithm are the feature dimension reduction techniques used to acquire better SER performance in this work. The proposed SER system is analyzed in both clean and noisy environments. The EMO-DB and IEMOCAP emotion databases are considered for evaluating the proposed SER performance. For noise analysis, the clean speech is corrupted with different noises of Aurora noise database and white Gaussian noise at different Signal to Noise Ratio (SNR) levels from −5dB to 20 dB. Support Vector Machine (SVM) classifier with linear and Radial Basis Function (RBF) kernels using 10-fold cross-validation and hold-out validation is used in this analysis with classification accuracy and computation time as the performance metrics. The results show that the proposed SER system outperforms the baseline SER system as well as many of the existing literature works both in clean and noisy conditions. For SNR levels >15 dB, the proposed SER system in presence of different noises performs same as the SER in clean environments. Whereas, for lower SNRs <15 dB the performance is likely to be reduced. Therefore, to overcome this drawback and improve the SER performance in noisy conditions, a dense Non-Negative Matrix Factorization (denseNMF) method is adopted for de-noising the noisy speech signal prior to SER achieving noise robustness.

Mixture linear prediction Gammatone Cepstral features for robust speaker verification under transmission channel noise

In this paper, we present a Mixture Linear Prediction based approach for robust Gammatone Cepstral Coefficients extraction (MLPGCCs). The proposed method provides performance improvement of Automatic Speaker Verification (ASV) using i-vector and Gaussian Probabilistic Linear Discriminant Analysis GPLDA modeling under transmission channel noise. The performance of the extracted MLPGCCs was evaluated using the NIST 2008 database where a single channel microphone recorded conversational speech. The system is analyzed in the presence of different channel transmission noises such as Additive White Gaussian (AWGN) and Rayleigh fading at various Signals to Noise Ratio (SNR) levels. The evaluation results show that the MLPGCCs features are a promising way for the ASV task. Indeed, the speaker verification performance using the MLPGCCs proposed features is significantly improved compared to the conventional Gammatone Frequency Cepstral Coefficients (GFCCs) and Mel Frequency Cepstral Coefficients (MFCCs) features. For speech signals corrupted with AWGN noise at SNRs ranging from (-5 dB to 15 dB), we obtain a significant reduction of the Equal Error Rate (EER) ranging from 9.41% to 6.65% and 3.72% to 1.50%, compared with conventional MFCCs and GFCCs features respectively. In addition, when the test speech signals are corrupted with Rayleigh fading channel we achieve an EER reduction ranging from 23.63% to 7.8% and from 10.88% to 6.8% compared with conventional MFCCs and GFCCs, respectively. We also found that the combination of GFCCs and MLPGCCs gives the highest performance of speaker verification system. The best performance combination achieved is around EER from 0.43% to 0.59% and 1.92% to 3.88%.