MFCC Features Research Articles

Post-Stroke Dysarthria Voice Recognition based on Fusion Feature MSA and 1D

Post-stroke Dysarthria (PSD) is one of the common sequelae of stroke. PSD can harm patients’ quality of life and, in severe cases, be life-threatening. Most of the existing methods use frequency domain features to recognize the pathological voice, which makes it hard to completely represent the characteristics of pathological voice. Although some results have been achieved, there is still a long way to go for practical applications. Therefore, an improved deep learning-based model is proposed to classify between the pathological voice and the normal voice, using a novel fusion feature (MSA) and an improved 1D ResNet network hybrid bi-directional LSTM with dilated convolution (named 1D DRN-biLSTM). The experimental results show that our fusion features bring greater improvement in pathological speech recognition than the method that only analyzes the MFCC features, and can better synthesize the hidden features that characterize pathological speech. In terms of model structure, the introduction of dilated convolution and LSTM can further improve the performance of the 1D Resnet network, compared to ordinary networks such as CNN and LSTM. The accuracy of this method reaches 82.41% and 100% at the syllable level and speaker level, respectively. Our scheme outperforms other existing methods in terms of feature learning capability and recognition rate, and will help to play an important role in the assessment and diagnosis of PSD in China.

Identification of Speaker from Disguised Voice Using MFCC Feature Extraction, Chi-Square and Classification Technique

Identification of Speaker from Disguised Voice Using MFCC Feature Extraction, Chi-Square and Classification Technique

Optimizing avian species recognition with MFCC features and deep learning models

Optimizing avian species recognition with MFCC features and deep learning models

Automatic Age and Gender Recognition Using Ensemble Learning

The use of speech-based recognition technologies in human–computer interactions is increasing daily. Age and gender recognition, one of these technologies, is a popular research topic used directly or indirectly in many applications. In this research, a new age and gender recognition approach based on the ensemble of different machine learning algorithms is proposed. In the study, five different classifiers, namely KNN, SVM, LR, RF, and E-TREE, are used as base-level classifiers and the majority voting and stacking methods are used to create the ensemble models. First, using MFCC features, five base-level classifiers are created and the performance of each model is evaluated. Then, starting from the one with the highest performance, these classifiers are combined and ensemble models are created. In the study, eight different ensemble models are created and the performances of each are examined separately. The experiments conducted with the Turkish subsection of the Mozilla Common Voice dataset show that the ensemble models increase the recognition accuracy, and the highest accuracy of 97.41% is achieved with the ensemble model created by stacking five classifiers (SVM, E-TREE, RF, KNN, and LR). According to this result, the proposed ensemble model achieves superior accuracy compared to similar studies in recognizing age and gender from speech signals.

Emotion Recognition in Lhasa Tibetan Speech based on Bi-LSTM Graph Convolutional Networks

Speech Emotion Recognition (SER) is a crucial component in the field of Human-Computer Interaction (HCI), with significant research and practical application implications. However, due to the complexity of the Tibetan language and the scarcity of datasets caused by the difficulty in collecting various dialects, there are not many research achievements in Tibetan speech recognition. Based on the foundation of constructing a TBLS1 dataset containing 6,000 Tibetan-language speech samples, an approach was devised for Tibetan speech emotion recognition. This approach leverages MFCC features and incorporates a Bi-directional Long Short-Term Memory (Bi-LSTM) network within a graph convolutional neural network. Finally, by comparing the performance of different models on this dataset, we demonstrated the feasibility of our model for Tibetan speech emotion recognition.

Speaker Identification Using MFCC Feature Extraction ANN Classification Technique

Speaker Identification Using MFCC Feature Extraction ANN Classification Technique

Text-to-Speech Synthesis for Hindi Language Using MFCC and LPC Feature Extraction Techniques

Text-to-Speech Synthesis for Hindi Language Using MFCC and LPC Feature Extraction Techniques

Enhancing Qur'anic Recitation Experience with CNN and MFCC Features for Emotion Identification

In this study, MFCC feature extraction and CNN algorithms are used to examine the identification of emotions in the murottal sounds of the Qur'an. A CNN model with labelled emotions is trained and tested, as well as data collection of Qur'anic murottal voices from a variety of readers using MFCC feature extraction to capture acoustic properties. The outcomes show that MFCC and CNN work together to significantly improve emotion identification. The CNN model attains an accuracy rate of 56 percent with the Adam optimizer (batch size 8) and a minimum of 45 percent with the RMSprop optimizer (batch size 16). Notably, accuracy is improved by using fewer emotional parameters, and the Adam optimizer is stable across a range of batch sizes. With its insightful analysis of emotional expression and user-specific recommendations, this work advances the field of emotion identification technology in the context of multitonal music.

Emotional voice conversion using DBiLSTM-NN with MFCC and LogF0 features

Emotional voice conversion using DBiLSTM-NN with MFCC and LogF0 features

ADAM optimised human speech emotion recogniser based on statistical information distribution of chroma, MFCC, and MBSE features

ADAM optimised human speech emotion recogniser based on statistical information distribution of chroma, MFCC, and MBSE features

Speech emotion recognition using a combination of variational mode decomposition and Hilbert transform

The objective of automated speech emotion recognition (SER) is to recognize each emotion of the speech signal uniquely and efficiently using machines like computers, mobile devices, etc. The popularity of SER has been widely acknowledged among researchers due to its extensive applicability in practical contexts. The use of SER has shown to be advantageous in several domains, including medical treatment, enhancement of security systems, surveillance operations, online marketing strategies, online educational platforms, online search engines, personal communication, customer relationship management, reinforcement of machine and human connection, and numerous other areas. Numerous authors have used various techniques, including the combination of multiple features (acoustic, non-acoustic, or both) and classifiers (machine learning, deep learning, or both), in order to enhance the efficacy of emotion categorization. In the present work, our objective is to enhance the performance of emotion classification (PECL) by using a combined approach of the variational mode decomposition (VMD) and Hilbert transform (HT) techniques. Using the VMD method, we decomposed the speech signal frame into many sub-signals, or intrinsic mode functions (IMFs). Then HT is applied to each VMD-based IMF signal to find the mode instantaneous amplitude (MIA) and mode instantaneous frequency (MIF) signal vectors. We extracted proposed features such as HT-based approximate entropy (HTAE), HT-based permutation entropy (HTPE), HT-based increment entropy (HTIE), and HT-based sample entropy (HTSE) using each MIA and MIF signal vector. The combination of the proposed HT-based features is called HT-based entropy (HTE) features. Then, we accessed the PECL using the HTE and MFCC features alone and in conjunction with a deep neural network (DNN) classifier. The experiment's results showed that the combinations of the proposed feature (MFCC + HTE) using a DNN classifier outperformed the individual features and obtained a SER accuracy of 86.92% for the EMOVO dataset and 91.63% for the EMO-DB dataset.

Enhancing robotic manipulator fault detection with advanced machine learning techniques

The optimization of rotating machinery processes is crucial for enhanced industrial productivity. Automatic machine health monitoring systems play a vital role in ensuring smooth operations. This study introduces a novel approach for fault diagnosis in robotic manipulators through motor sound analysis to enhance industrial efficiency and prevent machinery downtime. A unique dataset is generated using a custom robotic manipulator to examine the effectiveness of both deep learning and traditional machine learning in identifying motor anomalies. The investigation includes a two-stage analysis, initially leveraging 2D spectrogram features with neural network architectures, followed by an evaluation of 1D MFCC features using various conventional machine learning algorithms. The results reveal that the proposed custom CNN and 1D-CNN models significantly surpass traditional methods, achieving an F1-score exceeding 92%, highlighting the potential of sound analysis for automated fault detection in robotic systems. Additional experiments were carried out to investigate 1D MFCC features with various machine learning algorithms, including KNN, DT, LR, RF, SVM, MLP, and 1D-CNN. Augmented with additional data collected from the locally designed manipulator, our experimental setup significantly enhances model performance. Particularly, the 1D-CNN stands out as the top-performing model on the augmented dataset.

Human Scream Detection and Analysis to Control Crime Rate using Machine Learning

Public safety is significantly hampered by delayed police response due to a lack of accurate and timely information about crimes. Human scream detection using audio classification offers a promising solution. This work presents a novel three- phase scream detection system leveraging a K-Nearest Neighbors (KNN) classifier and a Multilayer Perceptron (MLP) model. The system first separates human distress sounds from back- ground noise using MFCC features and KNN. Subsequently, it differentiates screams from shouts within the distress category using another KNN classifier. Finally, the classified screams trigger emergency notifications sent to the police station via the Twilio library. Our proposed system offers a robust and layered approach to scream detection, potentially enhancing response times and improving public safety. Index Terms—MFCCs, KNN, Multilayer perceptron model, Scream Detection.

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.

A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds

A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds

A Comparative Study of Machine Learning Methods for Baby Cry Detection Using MFCC Features

The vocalization of infants, commonly known as baby crying, represents one of the primary means by which infants effectively communicate their needs and emotional states to adults. While the act of crying can yield crucial insights into the well-being and comfort of a baby, there exists a dearth of research specifically investigating the influence of the audio range within a baby cry on research outcomes. The core problem of research is the lack of research on the influence of audio range on baby cry classification on machine learning. The purpose of this study is to ascertain the impact of the duration of an infant’s cry on the outcomes of machine learning classification and to gain knowledge regarding the accuracy of results F1 score obtained through the utilization of the machine learning method. The contribution is to enrich an understanding of the application of classification and feature selection in audio datasets, particulary in the context of baby cry audio. The utilized dataset, known as donate-a-cry-corpus, encompasses five distinct data classes and possesses a duration of seven seconds. The employed methodology consists of the spectrogram technique, cross-validation for data partitioning, MFCC feature extraction with 10, 20, and 30 coefficients, as well as machine learning models including Support Vector Machine, Random Forest, and Naïve Bayes. The findings of this study reveal that the Random Forest model achieved an accuracy of 0.844 and an F1 score of 0.773 when 10 MFCC coefficients were utilized and the optimal audio range was set at six seconds. Furthermore, the Support Vector Machine model with an RBF kernel yielded an accuracy of 0.836 and an F1 score of 0.761, while the Naïve Bayes model achieved an accuracy 0.538 and F1 score of 0.539. Notably, no discernible differences were observed when evaluating the Support Vector Machine and Naïve Bayes methods across the 1-7 second time trial. The implication of this research is to establish a foundation for the advancement of premature illness identification techniques grounded in the vocalizations of infants, thereby facilitating swifter diagnostic processes for pediatric practitioners.

A novel Approach for Audio-based Video Analysis via MFCC Features

The video analysis is a momentous task of computer vision where larger videos are analyzed and converted to comparatively shorter summaries with key-frames satisfying a typical criterion. However, in the recent times audio-based video analysis is an important field where, audio features are used to categorize video frames into various classes. In this work, we present an audio-based video analysis model named as ABVS. The proposed approach employs 40 MFCC audio features from input audios to learn a multiclass classifier. The ABVS model is trained on ANN, SVM, KNN, DT and a majority voting ensemble to categorize a given video based on audio at high precision and low error rate. Our proposed approach is trained and validated on a benchmark urbansound8k dataset with an accuracy of 90% and loss of 0.10 on ANN and SVM model whereas, KNN achieves an accuracy of 89%. The ABVS model can be deployed in real-time applications to extract key-frames from the video scenes to troubleshoot the malfunctioning of critical infrastructure in industrial sectors. Our proposed model may be deployed in audio forensics for criminal voice investigation.

Enhancing Audio Classification Through MFCC Feature Extraction and Data Augmentation with CNN and RNN Models

Enhancing Audio Classification Through MFCC Feature Extraction and Data Augmentation with CNN and RNN Models

Enhancing Audio Classification Through MFCC Feature Extraction and Data Augmentation with CNN and RNN Models

Enhancing Audio Classification Through MFCC Feature Extraction and Data Augmentation with CNN and RNN Models

Mining the Performance Characteristics of Yao Nationality Musical Instruments under Multivariate Statistical Analysis

Abstract In the context of the rapid development of modernization and urbanization, the inheritance and research of music and musical instruments by ethnic minorities are facing great challenges. It is, therefore, of enormous significance to uncover the performance characteristics of ethnic minority musical instruments. This paper focuses on four categories of Yao musical instruments, namely reed instruments, air-pipe instruments, wind instruments, and percussion instruments. We mine the performance features of Yao musical instruments using MFCC feature extraction, perceptual linear prediction parameter extraction, and other methods. The performance of this paper’s algorithm is explored by comparing the detection and recognition accuracy of its algorithm with SVM on four types of musical instruments. The performance characteristics of Yao musical instruments are explored by analyzing the timbre characteristics, auditory characteristics, and beat statistics of the four instruments. This paper’s algorithm significantly outperforms the SVM algorithm in the recognition correct rate of four different types of musical instruments, with differences of 2.1905%, 7.1574%, 5.3758%, and 3.6962%, respectively. The extracted performance features of Yao music instruments reveal that reed instruments and air-pipe instruments have a superior timbral effect than wind instruments and percussion instruments. The sound of pneumatic instruments and wind instruments is the best when it comes to audibility, and the beats of reed instruments and wind instruments are the best among the four instruments.