Traditional Mel Frequency Cepstral Coefficients Research Articles

Acoustic tunnel lining cavity detection using cepstral coefficients with optimized filter bank

Tunnels are an essential component of modern transportation infrastructure, and their structural health is critical to traffic safety, which can be seriously affected by tunnel lining cavities. In this paper, an acoustic-based detection approach for assessing the integrity of tunnel linings is studied. By tapping the tunnel lining surface, acoustic signals are sampled and analyzed using a novel feature parameter extraction algorithm-the energy-frequency cepstral coefficient, which uses wavelet packet decomposition to obtain energy distribution statistics in the frequency domain of the signal, and constructs a signal-dependent filter bank to achieve the cepstral coefficient extraction. Compared with the traditional Mel filter bank, this method can adaptively adjust the resolution of the filter bank according to the frequency characteristics of the classified samples. This allows for higher frequency resolution in regions where the energy distribution is concentrated. As a result, the extracted feature parameters achieve both dimensional compression and superior information retention. Experimental results show that the proposed energy-frequency cepstral coefficient feature outperforms the traditional Mel-frequency cepstral coefficient feature, resulting in a higher accuracy of tunnel lining detection. The convolutional neural network model achieves an accuracy of 99.2%, with a 78.9% reduction in error rate compared with the traditional Mel-frequency cepstral coefficient feature parameters. Additionally, a particle swarm optimization support vector machine model is trained to achieve an accuracy rate of 99.6% and an error rate reduction of 76.5%.

Highly discriminative and adaptive feature extraction method based on NMF–MFCC for event recognition of Φ-OTDR

To enhance the capability of phase-sensitive optical time domain reflectometers (Φ-OTDR) to recognize disturbance events, an improved adaptive feature extraction method based on NMF–MFCC is proposed, which replaces the fixed filter bank used in the traditional method to extract the mel-frequency cepstral coefficient (MFCC) features by a spectral structure obtained from the Φ-OTDR signal spectrum using nonnegative matrix factorization (NMF). Three typical events on fences are set as recognition targets in our experiments, and the results show that the NMF–MFCC features have higher distinguishability, with the corresponding recognition accuracy reaching 98.47%, which is 7% higher than that using the traditional MFCC features.

Automatic speaker verification system for dysarthric speakers using prosodic features and out-of-domain data augmentation

A communication disorder is an impairment of a person’s ability to talk or communicate appropriately. Dysarthria is a common neuro-motor speech communication disorder that can be caused by neurological damage. Dysarthria may affect the articulation, phonation, and prosody of a speaker. Dysarthria patients have poor neuromotor coordination and other physical impairments, making it difficult to utilize an interactive keyboard or other user interfaces. The ASV system can make biometric applications more accessible to dysarthric speakers by eliminating the need for them to remember cumbersome and unique authentication numbers and passwords. In this paper, we presented a study on developing an automatic speaker verification (ASV) system for dysarthria patients with varying speech intelligibility to assist them in remote access control and voice-based biometric applications. In the initial part of our proposed approach, we included a duration modification-based data augmentation module in the front end of the ASV system. Since prosody deficits are one of the early indicators of dysarthria, we investigated the role of prosodic variables in combination with the traditional Mel-frequency cepstral coefficients (MFCC). The prosodic variables explored in this study include pitch, loudness, and voicing probability. Separate i-vector and x-vector models are trained and compared using individual MFCC, prosodic variables, and their combinations. The experimental results showed that the proposed approach based on combining MFCC and prosody features along with duration-modification-based data augmentation produced promising results.

PLDA in i-vector based underwater acoustic signals classification

ABSTRACT Intelligent recognition of underwater acoustic targets is crucial for exploiting marine resources. In this paper, we propose a deep learning method for underwater acoustic signal recognition consisting of three steps: Firstly, we extract the underwater acoustic signal's identification vector (i-vector) using a Gaussian mixture model. Secondly, we construct a probabilistic linear discriminant analysis (PLDA) model that divides the i-vector into two segments, Finally, we used a multi-long short-term memory neural network (MLSTMNN) to learn the features, outputting the underwater acoustic signal labels through the softmax layer. Experiments using the ShipsEar dataset can obtain a recognition rate of 84.8%; compared to the traditional Mel frequency Cepstral Coefficients (MFCC) and convolutional neural networks, the recognition rate greatly improved.

Hierarchical Multi-Class Classification of Voice Disorders Using Self-Supervised Models and Glottal Features

Previous studies on the automatic classification of voice disorders have mostly investigated the binary classification task, which aims to distinguish pathological voice from healthy voice. Using multi-class classifiers, however, more fine-grained identification of voice disorders can be achieved, which is more helpful for clinical practitioners. Unfortunately, there is little publicly available training data for many voice disorders, which lowers the classification performance on data from unseen speakers. Earlier studies have shown that the usage of glottal source features can reduce data redundancy in detection of laryngeal voice disorders. Another approach to tackle the problems caused by scarcity of training data is to utilize deep learning models, such as wav2vec 2.0 and HuBERT, that have been pre-trained on larger databases. Since the aforementioned approaches have not been thoroughly studied in the multi-class classification of voice disorders, they will be jointly studied in the present work. In addition, we study a hierarchical classifier, which enables task-wise feature optimization and more efficient utilization of data. In this work, the aforementioned three approaches are compared with traditional mel frequency cepstral coefficient (MFCC) features and one-vs-rest and one-vs-one SVM classifiers. The results in a 3-class classification problem between healthy voice and two laryngeal disorders (hyperfunctional dysphonia and vocal fold paresis) indicate that all the studied methods outperform the baselines. The best performance was achieved by using features from wav2vec 2.0 LARGE together with hierarchical classification. The balanced classification accuracy of the system was 62.77% for male speakers, and 55.36% for female speakers, which outperformed the baseline systems by an absolute improvement of 15.76% and 6.95% for male and female speakers, respectively.

Heart sound classification based on improved mel frequency cepstrum coefficient and integrated decision network method

Heart sound analysis is significant for early diagnosis of congenital heart disease. A novel method of heart sound classification was proposed in this paper, in which the traditional mel frequency cepstral coefficient (MFCC) method was improved by using the Fisher discriminant half raised-sine function (F-HRSF) and an integrated decision network was used as classifier. It does not rely on segmentation of the cardiac cycle. Firstly, the heart sound signals were framed and windowed. Then, the features of heart sounds were extracted by using improved MFCC, in which the F-HRSF was used to weight sub-band components of MFCC according to the Fisher discriminant ratio of each sub-band component and the raised half sine function. Three classification networks, convolutional neural network (CNN), long and short-term memory network (LSTM), and gated recurrent unit (GRU) were combined as integrated decision network. Finally, the two-category classification results were obtained through the majority voting algorithm. An accuracy of 92.15%, sensitivity of 91.43%, specificity of 92.83%, corrected accuracy of 92.01%, and F score of 92.13% were achieved using the novel signal processing techniques. It shows that the algorithm has great potential in early diagnosis of congenital heart disease.

A Novel Driving Noise Analysis Method for On-Road Traffic Detection.

Effective noise reduction and abnormal feature extraction are important for abnormal sound detection occurring in urban traffic operations. However, to improve the detection accuracy of continuous traffic flow and even overlapping vehicle bodies, effective methods capable to achieve accurate signal-to-noise ratio and appropriate characteristic parameters should be explored. In view of the disadvantages of traditional traffic detection methods, such as Short-Time Energy (STE) and Mel Frequency Cepstral Coefficients (MFCC), this study adopts an improved spectral subtraction method to analyze traffic noise. Through the feature fusion of STE and MFCC coefficients, an innovative feature parameter, E-MFCC, is obtained, assisting to propose a traffic noise detection solution based on Triangular Wave Analysis (TWA). APP Designer in MATLAB was used to establish a traffic detection simulation platform. The experimental results showed that compared with the accuracies of traffic detection using the traditional STE and MFCC methods as 67.77% and 76.01%, respectively, the detection accuracy of the proposed TWA is significantly improved, attaining 91%. The results demonstrated the effectiveness of the traffic detection method proposed in solving the overlapping problem, thus achieving accurate detection of road traffic volume and improving the efficiency of road operation.

GIS Mechanical Fault Diagnosis Method Based on Middle Time Mel Cepstrum Coefficient

Mechanical fault is a common fault of gas insulated switchgear (GIS). If not found in time, it will cause major safety hazards such as opening and closing fault. In this paper, a diagnosis method based on improved Mel cepstrum coefficient for GIS mechanical fault on-line monitoring is proposed. Firstly, the Mel frequency cepstral coefficients (MFCC) are extracted from the preprocessed sound signals; in order to adapt to the characteristics of smooth sound energy change in GIS operation, the MFCC is optimized to obtain improved features; Support Vector Machine (SVM) is introduced to build a GIS mechanical fault diagnosis model based on acoustics and uses bagging algorithm to integrate the SVM model. In this study, mechanical fault is simulated on real GIS to obtain real fault sound signals for training and testing. The experimental results show that compared with the traditional MFCC, the improved MFCC has a higher recognition accuracy in GIS fault sound recognition system. The F1-score is generally over 80%, and the F1-score of specific mechanisms can even reach 99%.

Evaluation of Simultaneous Speech Detection Based on MFCC-DTW with Two-Stage Normalization

In Air Traffic Control a serious safety risk is represented by undetected simultaneous transmissions from different airplanes. In this paper, we approach this issue through a speech analysis algorithm, which combines traditional Mel Frequency Cepstral Coefficients extraction, a new two-stage normalization and widely used Dynamic Time Warping. In this way, we were able to extend the simultaneous speech detection capability in Voice Communication Systems of Air Traffic Control. The results prove that this implementation is suitable for practical applications.

Urban noise recognition with convolutional neural network

Urban noise recognition play a vital role in city management and safety operation, especially in the recent smart city engineering. Exiting studies on urban noise recognition are mostly based on conventional acoustic features, such as Mel-Frequency Cepstral Coefficients (MFCC) and Linear Prediction Cepstral Coefficients (LPCC), and the shallow structure based classifiers, such as support vector machine (SVM). However, the urban acoustic environment is complicated and changeable. Conventional acoustic representation and recognition methods may be insufficient in characterizing urban noises, and generally suffer from a degraded performance. In this paper, we study the recent deep neural network based urban noise recognition. The log-Mel-spectrogram, namely, the FBank feature is first derived for acoustic representation. Then, the FBank spectrum constructed with a set of FBank feature vectors from multiple acoustic signal frames is fed to a convolutional neural network (CNN) for urban noise recognition. Comprehensive studies on the dimension of FBank spectrums and the parameters in CNN, including the size of learnable kernels, the dropout rate, and the activation function, etc., are presented in the paper. An acoustic database collected in real environment covering 11 most common urban noises with more than 56,000 samples is constructed for model verification and performance evaluation. In addition, the traditional LPCC and MFCC acoustic feature combining with two popular machine learning algorithms, extreme learning machine (ELM) and support vector machine (SVM), and the FBank image feature combining with extreme learning machine (ELM), hierarchical extreme learning machine (H-ELM) and multilayer extreme learning machine (ML-ELM), have also been presented for discussions. Experimental results show that the proposed method generally outperforms conventional shallow structure based classifiers.

Deep Learning Methods for Underwater Target Feature Extraction and Recognition.

The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM) was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.

Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering

Due to the profound differences between acoustic characteristics of neutral and whispered speech, the performance of traditional automatic speech recognition (ASR) systems trained on neutral speech degrades significantly when whisper is applied. In order to deeply analyze this mismatched train/test situation and to develop an efficient way for whisper recognition, this study first analyzes acoustic characteristics of whispered speech, addresses the problems of whispered speech recognition in mismatched conditions, and then proposes a new robust cepstral features and preprocessing approach based on deep denoising autoencoder (DDAE) that enhance whisper recognition. The experimental results confirm that Teager-energy-based cepstral features, especially TECCs, are more robust and better whisper descriptors than traditional Mel-frequency cepstral coefficients (MFCC). Further detailed analysis of cepstral distances, distributions of cepstral coefficients, confusion matrices, and experiments with inverse filtering, prove that voicing in speech stimuli is the main cause of word misclassification in mismatched train/test scenarios. The new framework based on DDAE and TECC feature, significantly improves whisper recognition accuracy and outperforms traditional MFCC and GMM-HMM (Gaussian mixture density—Hidden Markov model) baseline, resulting in an absolute 31% improvement of whisper recognition accuracy. The achieved word recognition rate in neutral/whisper scenario is 92.81%.

Articulatory movement features for short-duration text-dependent speaker verification

During our pronunciation process, the position and movement properties of articulators such as tongue, jaw, lips, etc are mainly captured by the articulatory movement features (AMFs). This paper investigates to use the AMFs for short-duration text-dependent speaker verification. The AMFs can characterize the relative motion trajectory of articulators of individual speakers directly, which is rarely affected by the external environment. Therefore, we expect that, the AMFs are superior to the traditional acoustic features, such as mel-frequency cepstral coefficients (MFCC), to characterize the speaker identity differences between speakers. The speaker similarity scores measured by the dynamic time warping (DTW) algorithm are used to make the speaker verification decisions. Experimental results show that the AMFs can bring significant performance gains over the traditional MFCC features for short-duration text-dependent speaker verification task.

Passive Moving Target Classification Via Spectra Multiplication Method

Traditional feature extractions, such as mel-frequency cepstral coefficients (MFCCs), are susceptible to acoustic channel effects, reverberation, and additive environmental noises when applied to passive moving target classification in underwater environment. A spectra multiplication method (SMM) is proposed in this letter to replace the estimated spectrum of MFCCs. SMM suppresses the time-variant noise, and remarkably improves the discriminability of features with historical signals. Compared with traditional MFCCs, the proposed method shows consistent performance improvements in experiments with measured data under different parameter settings. The effect of multiplication order of SMM on classification accuracy has also been discussed. Since the SMM is generalized to a filter-based view, the relation between cutoff frequency and multiplication order is given. The change of classification accuracy induced by the multiplication order is in accord with the variation of cutoff frequency when designed by IIR filters.

SVM based Emotional Speaker Recognition using MFCC-SDC Features

Enhancing the performance of emotional speaker recognition process has witnessed an increasing interest in the last years. This paper highlights a methodology for speaker recognition under different emotional states based on the mul-ticlass Support Vector Machine (SVM) classifier. We compare two feature extraction methods which are used to represent emotional speech utterances in order to obtain best accuracies. The first method known as traditional Mel-Frequency Cepstral Coefficients (MFCC) and the second one is MFCC combined with Shifted-Delta-Cepstra (MFCC-SDC). Experimentations are conducted on IEMOCAP database using two multiclass SVM ap-proaches: One-Against-One (OAO) and One Against-All (OAA). Obtained results show that MFCC-SDC features outperform the conventional MFCC.

Improvement of automatic speech recognition systems via nonlinear dynamical features evaluated from the recurrence plot of speech signals

The spectral-based features, typically used in Automatic Speech Recognition (ASR) systems, reject the phase information of speech signals. Thus, employing extra features, in which the phase of the signal is not rejected, may fill this gap. Embedding the speech signal in the Reconstructed Phase Space (RPS) and then extracting some useful features from it, is a recently considered approach in this field. In this paper, we will follow this approach by evaluating some useful features from the Recurrence Plot (RP) of the embedded speech signals in the RPS; the proposed features are evaluated via applying a two-dimensional wavelet transform to the resulted RP diagrams. The proposed features are examined in an ASR task alone and in combination with the traditional Mel-Frequency Cepstral Coefficients (MFCC). For the second case, using English TIMIT corpus, 3.94% absolute classification accuracy improvement in the phoneme recognition accuracy rate, against using only the MFCC features is gained.

Automatic Recognition of Machinery Noise in the Working Environment

A necessity for the suitable recognition of different machinery and equipment based on the sound they generate is constantly present and will increase in the future. The main motivation for the discrimination between different types of machinery sounds is to develop algorithms that can be used not only for final quality inspection but for the monitoring of the whole production line. The objective of our study is to recognize the operation of the individual machine in a production hall, where background noise level is high and constantly changing. An experimental plan was designed and performed in order to confirm the hypothesis proposing that automatic speech recognition algorithms can be applied to automatic machine recognition. The design of the automatic machine recognition procedure used in our study was divided into three stages: feature extraction, training, and recognition (classification). Additionally, a traditional mel-frequency cepstral coefficient (MFCC) procedure was adjusted for machinery noise by using different filter compositions. Finally, two classifiers were compared, the k-NN classifier and the multivariate Gaussian distribution. The results of the experiment show that machinery noise features frequency cepstral coefficients (FCC) should be extracted by using linear filter compositions and processed with recognition algorithm based on the multivariate Gaussian distribution.

Robust Speaker Verification Using Improved PNCC Based on GMM-UBM

Focused on the issue that the robustness of traditional Mel Frequency Cepstral Coefficient (MFCC) feature degrades drastically in speaker verification in noisy environments, a kind of suitable extraction method for low SNR environments based on Gaussian Mixture Model‐Universal Background Model (GMM‐UBM) and improved Power Normalized Cepstral Coefficient (PNCC) is proposed. First, the PNCC feature is extracted after the Voice Activity Detection (VAD), which uses long term analysis to remove the effect of background noise. Then, Cepstral Mean Variance Normalization (CMVN), Feature Warping and other methods are used to improve PNCC. Finally, GMM‐UBM‐MAP is set as the baseline system for speaker verification test with TIMIT speech database, the robustness of four different features (MFCC, GFCC, PNCC and improved PNCC) are analyzed and compared in different noisy conditions. The experimental results indicate that MFCC has achieved the highest recognition rate under the environment of clean speech. By mixing the test speech with sine noises, the improved PNCC is more robust against different low‐SNR noises than other original features and its Equal Error Rate (EER) reduce significantly in low‐SNR noise environments.

Multi-resolution time frequency feature and complementary combination for short utterance speaker recognition

A human speaker recognition expert often observes the speech spectrogram in multiple different scales for speaker recognition, especially under the short utterance condition. Inspired by this action, this paper proposes a novel multi-resolution time frequency feature (MRTF) extraction method, which is obtained by performing a 2-Dimensional discrete cosine transform (DCT) in multi-scale on the time frequency spectrogram matrix and then selecting and combining to the final multi-scaled transformed elements. Compared to the traditional Mel-Frequency Cepstral Coefficient (MFCC) feature extraction, the proposed method can make better use of multi-resolution temporal-frequency information. Beyond this, we also proposed three complementary combination strategies of MFCC and MRTF: in feature level, in i-vector level and in score level. Comparing their performance. We found the best results are obtained by combination in i-vector level. In the three NIST 2008 Speaker Recognition Evaluation datasets, the proposed method is the most effective for improving the performance under short utterance than under long utterance. And after the combination, we can achieve an EER of 11.32 % and MinDCF of 0.054 in the 10sec-10sec trials on the male dataset, which is an absolute 3 % improvement of EER than the best reported result in this field.

Wavelet Cesptral Coefficients for Isolated Speech Recognition

The study proposes an improved feature extraction method that is called Wavelet Cepstral Coefficients (WCC). In traditional cepstral analysis, the cepstrums are calculated with the use of the Discrete Fourier Transform (DFT). Owing to the fact that the DFT calculation assumes signal stationary between frames which in practice is not quite true, the WCC replaces the DFT block in the traditional cepstrum calculation with the Discrete Wavelet Transform (DWT) hence producing the WCC. To evaluate the proposed WCC, speech recognition task of recognizing the 26 English alphabets were conducted. Comparisons with the traditional Mel-Frequency Cepstral Coefficients (MFCC) are done to further analyze the effectiveness of the WCCs. It is found that the WCCs showed some comparable results when compared to the MFCCs considering the WCCs small vector dimension when compared to the MFCCs. The best recognition was found from WCCs at level 5 of the DWT decomposition with a small difference of 1.19% and 3.21% when compared to the MFCCs for speaker independent and speaker dependent tasks respectively. DOI: http://dx.doi.org/10.11591/telkomnika.v11i5.2510 Full Text: PDF