Feature extraction using Spectral Centroid and Mel Frequency Cepstral Coefficient for Quranic Accent Automatic Identification

This paper proposes two models for Automatic Speaker Identification (ASI) task in the presence of interference. The first one uses the Normalized Pitch Frequency (NPF) and Mel- Frequency Cepstral Coefficients (MFCCs) as extracted features and multi-layer perceptron (MLP) as a classifier. In this model, we investigate the utilization of the Discrete Transform (DT) such as Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sin Transform (DST) to increase the robustness of extracted features against different types of degradation through exploit the sub-band decomposition characteristics of DWT and the energy compaction property of DCT and DST. This achieved by extracting features directly from speech signal contaminated with features extracted from Discrete transformed signals to create a hybrid feature vectors. The enhancement techniques such as Spectral Subtraction (SS), Winer Filter (WF) and Adaptive Wiener Filter as a preprocessing stage to eliminate the effect of the interference on the ASI performance. In the second model, we investigate the using of Deep Learning (DL) based Convolutional Neural Network (CNN) with the spectrogram and the Radon transform to increase the robustness of the ASI against the interference effects. One of this paper goals is making comparison between two models and reach to more robust ASI system against severe interference. The experimental results indicates that the two proposed models articulate satisfying results, the model-based CNN consuming time is less than that based MLP which requires large training epochs and using many techniques for feature extraction and enhancing performance.

show abstract

“…As seen in Fig. 3, the final step involves applying the DCT to the log of the Mel spectrum [20,27,39].…”

Section: Mel-frequency Cepstral Coefficients (Mfccs)mentioning

confidence: 99%

Automatic Speaker Identification System based MLP Network and Deep Learning in the Presence of Severe Interference

Shafik¹,

Sedik

Khalaf

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The spectral centroid of an acoustic signal frequency spectrum reflects the center where most of the energy in the frequency distribution is concentrated. It indicates whether the spectral structure of the signal contains a generality of low or high frequencies, respectively [28] [29]. The spectral centroid of the i th signal frame is computed as seen in equation ( 31…”

Section: Spectral Centroid (Sc)mentioning

confidence: 99%

Acoustic signal processing with robust machine learning algorithm for improved monitoring of particulate solid materials in a gas flowline

Aminu

McGlinchey

Cowell

2019

Flow Measurement and Instrumentation

View full text Add to dashboard Cite

Acoustic signal processing with robust machine learning algorithm for improved monitoring of particulate solid materials in a gas pipelineThe flow of particulate solid materials in a gas pipeline can significantly erode mechanical equipment, and hence, real-time quantitative monitoring is a timely need for the oil and gas industry. Although a considerable amount of research has been conducted employing acoustic signals for qualitative monitoring, there is still an unmet demand for a simple and robust quantitative monitoring system. Acoustic signal processing with machine learning is a simple and robust method that has the potential to meet this demand, but has not been previously used for particulate solid material quantitative monitoring. Here we report on the development of acoustic signal processing methods strictly on the existence and the significance of the correlation between emitted acoustic signals and the flow conditions and behaviours of particle-laden gas pipeline. The integrated, conventional Artificial Neural Network (ANN) models are used to capture the distribution of the acoustic feature vectors extracted from the signal processing techniques. The backpropagation learning method coupled with Grey wolf optimiser is used to adjust the weights of the network to minimize the regularized cost function for each feature vector. The Grey wolf optimiser is used to provide global adaptation strategy for the network hyper-parameters. The results from the signal processing techniques demonstrate a significant qualitative association between flow conditions and the emitted acoustic signature. Further, conventional ANN has mainly been concerned with capturing systematic patterns in a distribution of measurements fixed in time and the results of the processes are collected in discrete time intervals. Therefore, a modification of the classical ANN, called the Time Delay Neural Networks (TDNN) is used to capture such dynamics. The proposed method compares the performance of the classical ANN models with the TDNN models wherein the feature vectors were used to train the TDNN models.Results show that the TDNN models outperform the classical ANN models which confirm the fact that classical ANN models are insufficient for processing these time sequences. Overall, this study lays the basis for employing signal processing techniques in the development of a real-time quantitative particulate solid monitoring in a gas pipeline.

show abstract

“…The spectral centroid (S c ) of an acoustic signal frequency spectrum reflects the center where most of the energy in the frequency distribution is concentrated. It indicates whether the spectral structure of the signal contains a generality of low or high frequencies, respectively [35], [51]. The spectral centroid of the i th signal frame is computed as seen in Equation ( 16).…”

Section: Spectral Centroidmentioning

confidence: 99%

Optimal design for real-time quantitative monitoring of sand in gas flowline using computational intelligence assisted design framework

Aminu

McGlinchey

Chen

2019

Journal of Petroleum Science and Engineering

View full text Add to dashboard Cite

Global demand for oil and gas is still increasing rapidly. The direct consequence of this is the increased operating pressure amid concerns over increasing sand production. According to the Society of Petroleum Engineers (SPE), 70% of the world's hydrocarbon reserves are contained in reservoirs situated on unconsolidated formations. Given the reality of these formations, sand production will certainly be a problem of significant concern particularly during the later life of the fields when they become more 'mature'. However, to monitor sand and optimise its production for improved recovery and safety, life extension and economy of the fields and ensured reliability, the automatic detection and prediction of sand flow characteristic measurements; sand flow rate (SFR), sand concentration (SC), line pressure drop (PD), and gas velocity (GV), has become an important research topic of great interest. Despite this importance, discussion of the topic is still lacking in the literature. This paper proposes a novel and robust architecture of intelligent real-time sand flow characteristic measurement using an acoustic sensor and computational intelligence assisted design (CIAD) framework. It fully incorporates acoustic signal processing and analysis, prediction algorithms and optimisation algorithms in the design. Acoustic features based on acoustic signal processing techniques are extracted to reduce the dimensionality of the acoustic signals. A classical Artificial Neural Network (ANN) is used to model the non-linear relationships between the acoustic signal characteristics and the flow characteristics measurands. In addition, the ANN algorithm adapts its weights and biases using the Grey Wolf Optimiser (GWO) through minimisation of the cost function during the training phase. Preliminary results obtained on a laboratory test rig demonstrate that an acoustic sensor coupled with CIAD may provide simple and robust practical solution to the measurement problem of particle-laden gas flow characteristics in real-time.

show abstract

Feature extraction using Spectral Centroid and Mel Frequency Cepstral Coefficient for Quranic Accent Automatic Identification

Cited by 16 publications

References 18 publications

Automatic Speaker Identification System based MLP Network and Deep Learning in the Presence of Severe Interference

Automatic Speaker Identification System based MLP Network and Deep Learning in the Presence of Severe Interference

Acoustic signal processing with robust machine learning algorithm for improved monitoring of particulate solid materials in a gas flowline

Optimal design for real-time quantitative monitoring of sand in gas flowline using computational intelligence assisted design framework

Contact Info

Product

Resources

About