MFCC Algorithm Research Articles

The Application of Multimodal Discourse Analysis in Urban Intercultural Communication

Abstract This paper firstly analyzes the basic composition of intercultural communication ability, discusses the specific function of cultural promotion of urban tourism, and gives the promotion effect of intercultural communication on urban tourism. Secondly, the connotation of multimodal discourse analysis is given, and the technical analysis of text, audio, and visual features is carried out for the analysis of urban tourism discourse. Then, the TF-IDF algorithm is used to realize the feature extraction of tourism culture text, the MFCC algorithm is used to extract the audio features of tourism culture, and the modal classification network is used to realize the recognition of the visual features of urban tourism culture video. Finally, to verify the effectiveness of the application of multimodal discourse analysis in urban cross-cultural communication, three aspects were tested and analyzed respectively. The results show that the F1 value of the TF-IDF algorithm is 0.912, which is 17.07% higher than that of the CTF-TF-IDF algorithm. When the amount of audio recognition is 5GB, the recognition time of the MFCC audio recognition method is 10.4 s. When the weight value of the visual feature extraction network is set to 1.0, the highest visual feature extraction error rate is only 3.96%. Using multimodal discourse analysis to carry out urban tourism discourse analysis can realize more comprehensive urban tourism feature extraction, help tourists strengthen their tourism perception, and then promote the enhancement of urban cross-cultural communication ability.

A high performance-oriented AI-enabled IoT-based pest detection system using sound analytics in large agricultural field

The agricultural industry has enormous potential to meet the world's growing need for nutritious and healthful food. However, pests destroy a significant portion of the harvest and reduce quality; thus, farmers struggle to discover pests on their farms. Traditional pest identification methods require scientists with extensive field experience correctly identify pests based on their physical characteristics. Pesticides harm food and agriculture. IoT technology uses many affordable sensor devices to collect real-time data on pest-related agricultural development characteristics. The research paper aims to develop an AI-enabled real-time, IoT-based automatic pest detection system using sound pest analytics and IoT networks in the sizeable agricultural field. The proposed method used audio pre-processing techniques in sound analytics such as HPF, Hann window, hop window, FFT, DFT, STFT, and MFCC algorithm for denoising the pest sound, removing the spectral leakage, converting overlapping to non-overlapping frames, converting the time to the frequency domain, determining frequency spectrum, detecting sinusoidal frequency and internal component, extracting the MFCCs feature respectively. The characteristics and other statistical metrics were collected from 500 pest sounds and trained, validated, and evaluated using the CNN, LSTM, Bi-LSTM, and CNN-Bi-LSTM network models. The extracting features and different statistical measurements were compared during the testing process. The proposed system integrated the CNN and Bi-LSTM techniques called CNN-Bi-LSTM model for training, validating, and testing. From the experimental results, it has been observed that, the proposed CNN-Bi-LSTM model achieved 98.91 % accuracy, 96.8 % sensitivity, 97.96 % specificity, 98.54 % recall, 98.63 % precision, and 98.58 % F1 score, which is better compared to CNN, LSTM, Bi-LSTM and also existing ANN, DCNN, and VGG-16 state-of-the-art techniques.

Fault Diagnosis of Mine Hoist Based on MFCC-SVDD

In the field of coal mine production, mine hoist plays a very important role in the whole mine transportation engineering. Its safety and stability directly affect the production efficiency of coal mine and the life safety of staff. In view of this, a fault diagnosis method of mine hoist based on MFCC-SVDD is proposed. By collecting the audio signal of the elevator, MFCC algorithm was used to extract the sound signal of multiple channels and the MEL frequency cepstrum coefficient was used to extract the fault characteristic parameters. Based on the one-class classifier SVDD, the hypersphere of the elevator was constructed to test and recognize the sound signals in the training, and the classification and recognition of the fault types of the elevator were completed. The MFCC characteristic parameters of 600 training samples were randomly selected as input to train the model, and 200 test samples were identified. The accuracy of fault identification reached 85%-96%, which provided a guarantee for mine production safety.

Algorithms and architectures of speech recognition systems

Digital processing of speech signal and the voice recognition algorithm is very important for fast and accurate automatic scoring of the recognition technology. A voice is a signal of infinite information. The direct analysis and synthesis of a complex speech signal is due to the fact that the information is contained in the signal.
 Speech is the most natural way of communicating people. The task of speech recognition is to convert speech into a sequence of words using a computer program.
 This article presents an algorithm of extracting MFCC for speech recognition. The MFCC algorithm reduces the processing power by 53% compared to the conventional algorithm. Automatic speech recognition using Matlab.

Parallel Implementation of Nios Ii Multiprocessors, Cepstral Coefficients of Mel Frequency and MLP Architecture in Fpga: the Application of Speech Recognition

Speech processing in real time requires the use of fast, reconfigurable electronic circuits capable of handling large amounts of information generated by the audio source. This article presents hardware implementations of a multilayer perceptron (MLP) and the MFCC algorithm for speech recognition. These algorithms have been implemented in hardware and tested in an on-board electronic card based on a reconfigurable circuit (FPGA). We also present a comparative study between several architectures of MLP and with the literature on the level of costs with regard to the surface of silicon, the speed and the computing resources required. Following the FPGA circuit modification, we created NIOSII processors to physically implement the architecture of ANN-type MLPs and MFCC speech recognition algorithms and perform real-time speech recognition functions.

Python Language Training System Based on MFCC, VQ, Variational Coefficient and KNTM Algorithm

This contribution describes the second stage of the creation of a language training system programmed in Python with the aim of application to speech therapy in spanish-speaking countries, starting the study in Cuba. The first stage of this research was carried out in Matlab by analyzing the dynamics of change of the centroids of the codebooks, extracted from words pronounced by a locutor. As second stage, the Variational Coefficient formula is used in order to estimate the percentage of effectiveness with which the announcer performs voice training. A modified approach to programming the variational coefficient is taken into account as a measure of dispersion of a group of vectors. The modification is given by taking the mean of the group of vectors as the vector that represents the phonetic boundaries of the word to be trained. Besides, a novel approach for word recognition is used, based on the K-Nearest Training Matrix (KNTM) algorithm that lays its foundations in the analysis of matrix similarity taken the Frobenius norm as a measure to distinguish similar or non-similar characteristics of a matrix with respect to a database of matrices. To reduce the computational cost of the program and speed up its proper functioning, the training matrices of the database are saved in files with a .tex extension, in this way after training process, the program should only read them and not recalculate them, which significantly reduces the running time of the algorithm.

Speech Recognition Implementation Using MFCC and DTW Algorithm for Home Automation

The use of speech recognition as part of home automation, especially for smart homes, is an exciting thing that is still being developed. That is because of human needs for comfort, convenience, quality of life, and better safety. Speech recognition built in this study is used as a device to control smart home devices by identifying the commands spoken by users, especially in a state of clean speech. The command used is a predetermined consecutive word. For the extraction of voice commands, the MFCC algorithm is used to match spoken words with templates using the Dynamic Time Warping (DTW) algorithm. DTW algorithm can find the difference between 2-time series that have different lengths of time. The results of the accuracy of this system by using these algorithms were successfully carried out by 86.67%, with an average time required to identify the commands of 5.28 seconds.

SPEAKER IDENTIFICATION USING GMM WITH MFCC IN PYTHON

The concept of speaker identification falls into the study of processing the digital signal. The previous systems supported acoustic channel including phonetics which are built for Automatic Speech Recognition. To recognize the user these systems, use pattern matching. Over recent advancements in technology, voice recognition is now considered a very important aspect that provides security to one’s electronic gadgets. This technology has a potential to make our lives more safe and secure. In certain ways, such as biometrics that can authenticate the user on the basis of the features of his/her speech signal. This paper develops the improved approaches by the implementing MFCC algorithm along with GMM techniques to spot a speaker. Efficiency of proposed methods are demonstrated and discussed within the experimental study by real-time and live datasets.

SPEECH RECOGNITION BY IMPROVING THE PERFORMANCE OF ALGORITHMS USED IN DISCRIMINATION

Speech recognition techniques are one of the most important modern technologies. Many different systems have been developed in terms of methods used in the extraction of features and methods of classification. Voice recognition includes two areas: speech recognition and speaker recognition, where the research is confined to the field of speech recognition. The research presents a proposal to improve the performance of single word recognition systems by an algorithm that combines more than one of the techniques used in character extraction and modulation of the neural network to study the effects of recognition science and study the effect of noise on the proposed system. In this research four systems of speech recognition were studied, the first system adopted the MFCC algorithm to extract the features. The second system adopted the PLP algorithm, while the third system was based on combining the two previous algorithms in addition to the zero-passing rate. In the fourth system, the neural network used in the differentiation process was modified and the error ratio was determined. The impact of noise on these previous systems. The outcomes were looked at regarding the rate of recognizable proof and the season of preparing the neural network for every system independently, to get a rate of distinguishing proof and quiet up to 98% utilizing the proposed framework.

Insulation fault identification of vacuum circuit breakers based on improved MFCC and SVM

Insulation faults in vacuum circuit breakers can produce physical phenomena such as visible sound, ultrasound, and electromagnetic waves. Through the real-time collection and analysis of the discharge sound during the internal insulation failure of the circuit breaker, the insulation state of the circuit breaker can be judged. This article proposes a method. The improved MFCC algorithm is used to extract the characteristic parameters of the discharge signal.The recognition of the flashover discharge sound signal is achieved by one-class SVM. The one-class SVM is constructed, so one-class SVM can be used to identify whether the signal is a surface discharge or not. The characteristic vectors of the audio signal of discharge have intrinsic similarity, and the distribution can be concentrated, which is significantly different from other abnormal sounds. The conclusion is verified by experimental data. The calculation results show that the it can effectively identify the insulation state of vacuum circuit breaker by the method of using of MFCC feature extraction based on Fisher criterion and one-class support vector machine.

SPEECH RECOGNITION BY IMPROVING THE PERFORMANCE OF ALGORITHMS USED IN DISCRIMINATION

Speech recognition techniques are one of the most important modern technologies. Many different systems have been developed in terms of methods used in the extraction of features and methods of classification. Voice recognition includes two areas: speech recognition and speaker recognition, where the research is confined to the field of speech recognition. The research presents a proposal to improve the performance of single word recognition systems by an algorithm that combines more than one of the techniques used in character extraction and modulation of the neural network to study the effects of recognition science and study the effect of noise on the proposed system. In this research four systems of speech recognition were studied, the first system adopted the MFCC algorithm to extract the features. The second system adopted the PLP algorithm, while the third system was based on combining the two previous algorithms in addition to the zero-passing rate. In the fourth system, the neural network used in the differentiation process was modified and the error ratio was determined. The impact of noise on these previous systems. The outcomes were looked at regarding the rate of recognizable proof and the season of preparing the neural network for every system independently, to get a rate of distinguishing proof and quiet up to 98% utilizing the proposed framework.

Detection Algorithm of Trapped Personnel Based on Sound Processing Technology

In the China's major disasters, the equipment which is used to rescue trapped personnel has high cost, needs to carry and has low efficiency. In order to solve the problems, a detection algorithm of trapped personnel based on sound processing technology (DATP) is proposed. In the DATP algorithm, sound signal is collected. The data with large energy is selected. Preprocessing method is used, such as Kalman filter and normalization. FFT transform is used to frequency domain analysis. The data is extracted in the band of 18400-19240 Hz and 20811-22050 Hz. The corresponding similarity is calculated. According to the similarity values, whether there is trapped personnel is determined. The simulation results show that DATP algorithm improves recognition rate and reduces false judgment rate and computation time. In short, in the sound recognition of trapped personnel when major disaster occurs, DATP is better than MFCC algorithm, and is suitable for embedded devices.

一种特定人语音家居控制系统

语音控制在智能家居的应用为人民生活带来极大便利，但常规的非特定人语音控制会产生语音的误触发。本文在非特定语音识别的基础上，通过改进相应算法设计了一种特定人语音识别家居控制系统。系统采用MFCC算法获取语音特征，通过DTW算法实现语音特征匹配。上位机基于安卓平台，利用Android Studio工具并结合NDK组件实现相应软件与算法开发。下位机基于Zigbee平台，利用IAR完成家居系统下位机的开发。系统可完成特定人的语音控制，具有较高的识别率，操作更加人性化。 The application of speech control in smart home brings great convenience to life. However, con-ventional independent speech control will make incorrect speech triggering. Based on the non- specific speech recognition, this paper designs a specific human voice recognition home control system by improving the corresponding algorithm. This system gets speech features by MFCC al-gorithm and matches speech feature by DTW algorithm. Host computer is based on Android platform. This paper uses Android Studio tools and NDK assembly to achieve the development of software and algorithm. Lower computer is based on Zigbee platform used IAR to achieve lower computer development of smart home. As a result, this system can solve specific speech control with a higher recognition rate and more human operation.

임베디드 시스템에서 사용 가능한 적응형 MFCC와 Deep Learning 기반의 음성인식

This paper proposes a noble voice recognition method based on an adaptive MFCC and deep learning for embedded systems. To enhance the recognition ratio of the proposed voice recognizer, ambient noise mixed into the voice signal has to be eliminated. However, noise filtering processes, which may damage voice data, diminishes the recognition ratio. In this paper, a filter has been designed for the frequency range within a voice signal, and imposed weights are used to reduce data deterioration. In addition, a deep learning algorithm, which does not require a database in the recognition algorithm, has been adapted for embedded systems, which inherently require small amounts of memory. The experimental results suggest that the proposed deep learning algorithm and HMM voice recognizer, utilizing the proposed adaptive MFCC algorithm, perform better than conventional MFCC algorithms in its recognition ratio within a noisy environment.

Chinese Accent Detection Research Based on Features Structured

Accent is a critically important component of spoken communication, and plays a very important role in spoken communication. In this paper, we conduct accent by using MFCC algorithm and RASTA - PLP algorithm to extract short-time spectrum features of each speech segment based on features structured information. We build short-time spectrum feature sets based on MFCC algorithm and RASTA - PLP algorithm. And we choose NaiveBayes classifier to model the two feature sets. NaiveBayes is to choose the class with maximum posteriori probability as the object's class. This classification method makes full use of the related phonetic features of speech segment. Based on short-time spectrum of MFCC feature set and short-time spectrum of RASTA - PLP feature set respectively achieve 82.1% and 80.8% accent detection accuracy on ASCCD. The experimental results indicate that based on sub-segment splicing feature structured method of MFCC and sub-segment splicing feature structured method of RASTA - PLP can be used in Chinese accent detection study.

Improved Window Function in the Application of MFCC Feature Parameter Extraction

In view of spectrum leakage and the contradictory problem of spectrum accuracy of main lobe and reducing spectrum leakage, MFCC algorithm based on improved window function is proposed. Improved window function is based on the mathematical analysis of Kaiser window, and under the condition of finite sampling points minuses weighted impact function where is at the frequencies that side lobe peaks of correspond to. The amplitude of improved window compared with Kaiser window is smaller, and main lobe width is the same, solving the conflicting problem of main lobe width and side lobe amplitude and reducing spectrum leakage. The experimental results show that speech recognition rate of MFCC feature parameter extraction algorithm based on improved window function is better than Kaiser window and Hamming window.

Design of a Model Reference Cruise Control Algorithm

A methodology to design a model free cruise control algorithm(MFCC) is presented in this paper. General cruise control algorithms require lots of vehicle parameters to control the power train and the brake system, that makes control system complicate. Moreover, when the target vehicle is changed, the vehicle parameters should be reinvestigated in order to apply the cruise control algorithm to the subject vehicle. To overcome these disadvantages of the conventional cruise control algorithm, MFCC algorithm has been developed. The algorithm directly determines the throttle, brake inputs based on the reference model parameters such as clearance, relative velocity, and subject vehicle acceleration. This simple structure facilitates human centered design of cruise controller and makes it easy to apply control algorithm to various vehicles without reinvestigation of vehicle parameters. To achieve vehicle safety and driver comfort, control parameters of the model free cruise control algorithm has been designed using the real-world driving test data. Few parameters have been adapted using a learning algorithm to minimize the effects of unawareness of the vehicle parameters. From the simulation study, the performance of the proposed controller has been compared with that of the conventional adaptive cruise controller(ACC). It is shown that the proposed control strategy its behavior is not only similar to that of the conventional ACC in normal driving condition but also more robust than the ACC for model uncertainty and external disturbance. Language: en

Algorithm of Abnormal Audio Recognition Based on Improved MFCC

Characteristics extraction has a great effect on the audio training and recognition in the audio recognition system. MFCC algorithm is a typical characteristics extraction method with stable performance and high recognition rate. For the situation that MFCC has a large amount of computation, an improved algorithm MFCC_E is introduced. The computation of MFCC_E is reduced by 50% compared with the standard algorithm MFCC, and it make the hardware implementation is easy. The experimental result indicated that MFCC_E and MFCC have the same recognition rate roughly, yet the computational complexity of MFCC_E is much smaller.

Feature extraction for vowel recognition using mellin transform

This paper proposed a new feature extraction algorithm for vowel recognition using Mellin transform and MFCC. The scale transform is a particular restriction of the Mellin transform. The key property of the scale transform is the scale invariance. This algorithm consists of 3 main stages which are as follow. First stage contains, Extraction spectral envelope from vowels, by using cepstrum method. In the second stage, Mellin transform is used for mapping same vowels with different pitch and different vocal tract to the same waveforms. In third stage, we used a new MFCC algorithm in order to extract main parameters from the output of second stage. The new MFCC algorithm contains third and fourth order cumulant of log‐mel‐amplitudes. This new MFCC coefficients are robust in presence of additive white noise. Moreover, The LPC method has been used instead of MFCC method in third stage, Experimental result indicates that the new MFCC algorithm produced better result than LPC and original MFCC.