Endpoint Detection Algorithm Research Articles

Acoustic modulation signal recognition based on endpoint detection

The modulation recognition technology for acoustic signals holds significant research importance in signal demodulation and communication signal reconnaissance, serving as a crucial component and key aspect. This paper investigates the modulation recognition technology for acoustic signals (< 20 kHz) from the perspectives of signal preprocessing and feature extraction. Firstly, it selects seven modulation signals 2ASK, 4ASK, 2FSK, 4FSK, 2PSK, 4PSK, and OFDM as recognition targets and systematically compares the effectiveness of four different endpoint detection algorithms in modulation signal recognition. To further enhance the performance of the short-time energy entropy ratio algorithm, this study introduces three different noise reduction algorithms for optimization. Finally, to accurately identify and distinguish between 2 and 4FSK signals, this study optimizes the related algorithms of the cyclic spectrum by using the kurtosis coefficient value Kur of the cyclic spectrum parameter matrix when the cyclic frequency α = 0 to differentiate between these two signals. The results show that at SNR of 4 dB, the proposed modulation recognition algorithm can effectively distinguish between these two signals, achieving a recognition accuracy of over 99%.

Robust gesture recognition method toward intelligent environment using Wi-Fi signals

Wi-Fi-based gesture recognition represents an emerging paradigm of human–computer interaction. While deep learning-based and model-based solutions are crucial for improving accuracy and generalization performance, they often depend heavily on extensive datasets and the widespread deployment of sensing devices. In this paper, we address the challenge involving limited sensing data and devices. We propose a signal-based gesture recognition method that leverages gesture coding based on stroke trajectory and feature representation based on dynamic phase changes. Specifically, we develop an endpoint detection algorithm to ensure precise gesture recognition. Additionally, a subcarrier selection algorithm is designed to select optimal subcarriers, capturing comprehensive gesture information. Extensive experiments are conducted to evaluate the performance. Results demonstrate an average accuracy of 93.67% for six gestures. This approach effectively mitigates the impact of location and environment factors on gesture characteristics, and reduces dependence on large quantity of samples and transceiver devices, obviating the need for model training.

Research on Pig Sound Recognition Based on Deep Neural Network and Hidden Markov Models.

In order to solve the problem of low recognition accuracy of traditional pig sound recognition methods, deep neural network (DNN) and Hidden Markov Model (HMM) theory were used as the basis of pig sound signal recognition in this study. In this study, the sounds made by 10 landrace pigs during eating, estrus, howling, humming and panting were collected and preprocessed by Kalman filtering and an improved endpoint detection algorithm based on empirical mode decomposition-Teiger energy operator (EMD-TEO) cepstral distance. The extracted 39-dimensional mel-frequency cepstral coefficients (MFCCs) were then used as a dataset for network learning and recognition to build a DNN- and HMM-based sound recognition model for pig states. The results show that in the pig sound dataset, the recognition accuracy of DNN-HMM reaches 83%, which is 22% and 17% higher than that of the baseline models HMM and GMM-HMM, and possesses a better recognition effect. In a sub-dataset of the publicly available dataset AudioSet, DNN-HMM achieves a recognition accuracy of 79%, which is 8% and 4% higher than the classical models SVM and ResNet18, respectively, with better robustness.

Precise disturbance localization of long distance fiber interferometer vibration senor based on an improved time–frequency variation feature extraction scheme

Locating intrusions with high accuracy is crucial for prompting long distance distributed optical fiber vibration sensing systems to practical applications in engineering filed. To achieve the high measurement accuracy and real-time performance simultaneously, in this paper, an intensity-modulated ultra-long distance distributed optical fiber vibration sensing system using an asymmetric dual Mach-Zehnder interferometer is experimentally established. More importantly, a positioning approach based on an ameliorated time–frequency feature extraction scheme is proposed with both theoretically analysis and experimental demonstration. In particular, an endpoint detection algorithm based on differential operation is firstly utilized to rapidly and accurately locate the endpoints of the received vibration signals. Thus the large-band width signals can be successfully acquired by setting an approximate window. Then, the ameliorated time–frequency feature extraction scheme based on a maximal overlap discrete wavelet packet transform is applied to eliminate the asymmetry of the large-band width signals, as it could lead to an erroneous positioning result when directly using a cross-correlation time delay estimation algorithm. Finally, the vibration positions along the sensing fiber link of the established sensing system can be successfully demodulated with the help of the extracted time–frequency features. To validate the effectiveness of the proposed scheme, vibration positioning tests were conducted in a real perimeter security scenario. And the results show that a mean positioning error of 11.12 m and a mean processing time of 0.276 s have been realized in a sensing length of 101 km. Thus, it is believed that through continuous technological advancements and refine algorithm optimization, the long distance distributed optical fiber vibration sensor founded on the proposed positioning strategy is poised to play an important role in the practical engineering applications.

Artificial Intelligence Technology Enabling Innovation in Museum Public Cultural Service Models

Abstract In this paper, we constructed an artificial intelligence model of environment perception and human body perception, and after filtering the irrelevant information in the environment, we collected and analyzed the three-dimensional information of the environment to realize the intelligent perception of the environment. Aiming at the transient noise that may occur in the robot’s operating environment, a time threshold is added on the basis of the traditional double threshold endpoint detection algorithm, which effectively eliminates the influence of transient noise on endpoint detection and realizes non-contact continuous speech recognition. Then the data of the perceived human body was analyzed to understand the perception of the human body by artificial intelligence. Finally, a model for museum public cultural innovation services was constructed based on AI, and the effects of AI on public cultural services were analyzed. The results show that people’s overall perception of intelligent services is 4.305 points, and the perceived functionality, perceived ease of use, perceived pleasantness, and level of intelligence have a significant positive correlation with the quality of public cultural services, with β-values of 0.286, 0.206, 0.068, and 0.378, respectively, and p&lt;0.05.

Speech recognition and English corpus vocabulary learning based on endpoint detection algorithm

Speech recognition and English corpus vocabulary learning based on endpoint detection algorithm

Intelligent Speech Garbage Classification Based on Deep Residual Network

To solve the problem that there are many kinds of municipal solid waste and urban residents do not have a clear classification standard for garbage, an intelligent voice garbage classification system based on a deep residual neural network is designed. For the four kinds of common garbage in life, the voice commands of four kinds of typical garbage are collected. Through the speech endpoint detection algorithm, the silence and noise in the speech are removed, and the acoustic model based on the deep residual network is built to realize garbage classification. The experimental results show that after the model training is completed, the accuracy of the verification set reaches 98%, the accuracy of the test set reaches 96%, and the generalization ability is strong, which has a high application value.

Identification of oestrus cows based on vocalisation characteristics and machine learning technique using a dual-channel-equipped acoustic tag

Timely and accurate detection of oestrus in cows is an essential element of the good management of dairy farms. At present, the detection of cows in oestrus by acoustic means is impeded by the problems of filtering, incomplete feature selection, and poor recognition accuracy. To overcome these difficulties, this study proposes a sound detection method for cows in oestrus based on machine learning technology using an optimal feature combination and an optimal time window. Firstly, a dual-channel sound detection tag consisting of a unidirectional microphone and an omnidirectional microphone (OM) was developed. The Least Mean Squares adaptive algorithm based on wavelet thresholds was used to filter the signals from the OM, and the dual-channel endpoint detection algorithm was used to identify the lowing of individual cows. The Friedman analysis was then used to select the sound features with significant differences before and after oestrus in terms of time, frequency, and cepstrum, and these were used to determine the most acceptable feature combination. We then analysed the effects of Back Propagation Neural Network (BPNN), Cartesian Regression Tree, Support Vector Machine, and Random Forest classification on the accuracy, precision, sensitivity, specificity, and F1 score of oestrus discrimination. Different time windows were used, and the discrimination performance of these algorithms was evaluated using the Area under Receiver Operating Characteristic Curve to find the most satisfactory match between the time window and the recognition algorithm. The dual-channel acoustic tag’s accuracy, precision, sensitivity, and specificity results were 91.25, 98.83, 91.75, and 83.68%, respectively. BPNN with the 70 ms time window and the feature combination (spectral roll-off + spectral flatness + Mel-Frequency Cepstrum Coefficients) was confirmed as the most suitable oestrus recognition method. The average accuracy, precision, sensitivity, specificity, and F1 score of this method were 97.62, 98.07, 97.17, 97.19, and 97.63%, respectively. Based on these results, the approach was shown to be a feasible means of oestrus detection in dairy cows. Based on its ability to differentiate cows and its consistency, it was demonstrated that sound has the potential to replace accelerometers as an early indicator of oestrus in dairy cows.

Speech Recognition Robot using Endpoint Detection Algorithm

Controlling the machines and environment with speech makes human life easier and comfortable. In this direction a robot has been designed which can easily be controlled through the speech commands given by an authorised person. This work consists of two phases: Speech recognition and Robot control. Voice commands are given as an input, which is processed using the LabVIEW software. Speech processing is done using two algorithms: Endpoint detection algorithm and Silence removal algorithm. These algorithms differentiate the voice signal from the background noise, detect the word boundary and extract only the voiced part of the input signal and removing the background noise associated with it. The extracted voice command signal is then matched with the stored templates and on match, the code corresponding to a particular movement of robot is encoded and then transmitted to the robot controlling module via RF transmitter. RF receiver in robot controlling module receives the transmitted signal, which is decoded and applied as an input to microcontroller. The microcontroller interprets the code and initiates the robot movement depending on the command given. By giving proper command, robot can be made to stop, move forward, backward, turn left, turn right etc., This robot can be deployed in hazardous environment and can be controlled by an authorised person. It may also assist disabled people to carry out their daily work with ease.

Rope Jumping Strength Monitoring on Smart Devices via Passive Acoustic Sensing.

Rope jumping, as a fitness exercise recommended by many sports medicine practitioners, can improve cardiorespiratory capacity and physical coordination. Existing rope jump monitoring systems have limitations in terms of convenience, comfort, and exercise intensity evaluation. This paper presents a rope jump monitoring system using passive acoustic sensing. Our system exploits the off-the-shelf smartphone and headphones to capture the user's rope-jumping sound and breathing sound after exercise. Given the captured acoustic data, the system uses a short-time energy-based approach and the high correlation between rope jumping cycles to detect the rope-jumping sound frames, then applies a dual-threshold endpoint detection algorithm to calculate the number of rope jumps. Finally, our system performs regression predictions of exercise intensity based on features extracted from the jumping speed and the mel spectrograms of the user's breathing sound. The significant advantage of the system lies in the solution of the problem of poorly characterized mel spectrograms. We employ an attentive mechanism-based GAN to generate optimized breathing sound mel spectrograms and apply domain adversarial adaptive in the network to improve the migration capability of the system. Through extensive experiments, our system achieves (on average) 0.32 and 2.3% error rates for the rope jumping count and exercise intensity evaluation, respectively.

Signal identification based on modified filter bank feature and generalized regression neural network for optical fiber perimeter sensing

• Signal recognition method based on the generalized regression neural network (GRNN). • Feature extraction algorithm based on the modified filter bank (FB) feature. • Endpoint detection algorithm based on the short-time energy. • Little parameter adjustment and human influence in the training process. • High identification rate, short recognition time and broad application prospects. A method based on the modified filter bank (FB) feature and a generalized regression neural network (GRNN) is proposed to raise the accuracy and real-time performance of signal recognition in optical fiber perimeter sensing systems. The FB feature is modified by adding root mean square information of the signal power under the Mel filter bank. Four kinds of sensing signals under three types of weather conditions are obtained experimentally by a fenced perimeter sensing system based on an in-line Sagnac interferometer. The endpoint detection algorithm based on short-term energy is performed on the sensing signals to obtain the effective signal segments. Then the modified FB features of signal segments are extracted and randomly divided into training and testing samples. The optimal GRNN classifier model is generated by performing a 10-fold cross-validation on the training samples and used to recognize the testing samples. The average accuracy can reach 98.22 % and average recognition time is only about 0.07 s. This method is expected to meet the requirements for real-time and accuracy in practical application of optical fiber perimeter sensing signal recognition.

Optical Fiber Vibration Signal Recognition Based on the Fusion of Multi-Scale Features.

Because of the problem of low recognition accuracy in the recognition of intrusion vibration events by the distributed Sagnac type optical fiber sensing system, this paper combines the traditional optical fiber vibration signal recognition idea and the characteristics of automatic feature extraction by a convolutional neural network (CNN) to construct a new endpoint detection algorithm and a method of fusing multiple–scale features CNN to recognize fiber vibration signals. Firstly, a new endpoint detection algorithm combining spectral centroid and energy spectral entropy product is used to detect the vibration part of the original signal, which is used to improve the detection effect of endpoint detection. Then, CNNs of different scales are used to extract the multi–level and multi–scale features of the signal. Aiming at the problem of information loss in the pooling process, a new method of combining differential pooling features is used. Finally, a multi–layer perceptron (MLP) is used to recognize the extracted features. Experiments show that the method has an average recognition accuracy rate of 98.75% for the four types of vibration signals. Compared with traditional EMD and VMD pattern recognition and 1D–CNN methods, the accuracy of the optical fiber vibration signal recognition is higher.

Thought and Politics Teaching Students’ Mental Health Impact Model Based on Fuzzy Control Algorithm

The rapid development of modern science and technology has led to the increasing scale of production systems and the formation of large and complex systems, resulting in the increasing complexity of control objects, controllers, and control tasks and purposes. The problem of how to better play the nurturing function of professional courses and realize the combination of knowledge transfer and value leadership is addressed. Compared with traditional teaching methods, the combination of mental health knowledge and ideological and political content can effectively improve the life satisfaction of college students and thus promote the completion of teaching objectives. Based on the background of the current new social development, the values of college students are gradually tending to diversify, which brings certain difficulties to the development of thought and politics teaching in schools. In the new era, the psychological health and thought dynamics of college students are getting more and more attention from the society and schools. To establish positive and healthy “three views,” students are closely related to teaching of psychological fitness and thought and politics teaching. In this paper, we study the influence model of thought and politics teaching based on fuzzy control algorithm (FL) in order to achieve a scientific and systematic teaching method and good teaching effect. In this paper, the construction of FL-based thought and politics teaching students’ mental health influence model is studied, in order to achieve a scientific and systematic teaching method and good teaching effect. The experimental results show that the average correct rate of the endpoints corresponding to the endpoints detected by FL’s thought and politics teaching model is 76.99%, which is 42.85% higher than that of the nonlinear SISO system algorithm. Therefore, the endpoint detection algorithm of FL’s thought and politics teaching model combined with amplitude and phase information has a higher correct rate. Therefore, this paper can analyze the psychology of different groups of college students, so as to draw more accurate conclusions in the field of student psychology, and then improve the psychological health of individual college students. Therefore, the research in this paper can meet the intrinsic requirements of the psychological and ideological health development of college students, strengthen the theoretical research on the infiltration of teaching of psychological fitness into the teaching of civics, improve the teaching mode, and innovate the educational methods.

Oral Business English Recognition Method Based on RankNet Model and Endpoint Detection Algorithm

The prosodic feature of “stressed syllables” plays an important role in business English learning. For the majority of nonnative language learners learning English, the pronunciation of native language can easily affect the expression of spoken English. For those who cooperate and communicate in business, if they want to have more idiomatic and accurate spoken English, they need to control the necessary condition of stress first. This puts forward new requirements for the existing speech recognition technology: more accurate recognition of stressed syllables, reading complex and different emotional colors, and helping to correct oral expression. The experimental results show that (1) the higher the Fisher Ratio of the feature, the easier it is to distinguish the stressed syllables; adjusting the weight of features can effectively improve the recognition accuracy. (2) The recognition rate will decrease with the increase of noise. (3) InwMS method can distinguish features better than min-max method, but the recognition rate of stressed syllables is very low. Linear recognition based on single feature is not recommended. (4) The error rates of the two methods are 20.6% and 19.32%. If any feature of the fusion feature is removed, the error recognition rate of the model will increase by at least 3%. (5) For sentence stress recognition based on fusion features, the recognition error rate on RankNet model is as high as 42.51%. The final result of system operation is good, simple, and convenient.

Piano Music Teaching under the Background of Artificial Intelligence

The work is aimed at solving the problems of easy trapping into local extremes and slow convergence speed of the traditional music teaching evaluation system on Backpropagation Neural Network (BPNN). The traditional note recognition methods are susceptible to high noise complexity. Firstly, the Levenberg Marquardt (LM) algorithm is used to optimize the BPNN; secondly, an improved endpoint detection algorithm is proposed by short-term energy difference, which can accurately identify the time value of each note in the piano playing audio. By the traditional frequency domain analysis method, a radical frequency extraction algorithm is proposed by the improved standard harmonic method, which can accurately identify the note’s pitch. Finally, a piano performance evaluation model by BPNN is implemented, and the model is implemented by the Musical Instrument Digital Interface (MIDI) system. This evaluation model can be used to correct the errors of students’ performances in the piano music teaching process and to perform overall evaluation, rhythm evaluation, and expressive evaluation. Teachers and students play minuet to collect experimental samples to train BPNN and test the performance of the evaluation model. The practical result shows that (1) after 3000 times of training, the neural network error is less than 0.01, and the network converges; (2) the evaluation results of the piano performance evaluation model designed are basically in line with the actual level of the performer and have specific feasibility; and (3) the optimized BPNN is used to correct errors during performances with an accuracy rate of 94.3%, which is 5.25% higher than the traditional method. The error correction accuracy rate for pitch is 92.9%, which is 5.21% higher than the traditional method. The optimized BPNN has significantly improved the error correction accuracy of the notes and pitches played by the player. The model can effectively help piano beginners correct errors and improve the accuracy and efficiency of the practice. The purpose of this study is to alleviate the scarcity of piano teachers, reduce the work intensity of piano teachers, realize automatic error correction and objective evaluation of playing, and provide necessary technical support for improving the efficiency of piano music teaching.

Research on Endpoint Detection Algorithm in High Altitude Explosion Point Location Technology

Aiming at the problem of inadequate positioning accuracy of sound endpoints by the dual-element single-threshold endpoint detection algorithm and the single-element dual-threshold endpoint detection algorithm in the process of locating the sound source of weather modification bombs at high altitudes during artificial weather modification, a multi-element dual threshold endpoint detection algorithm. First, according to the characteristics of high-altitude explosion of weather modification bombs and ground reception, the sound signal is filtered and denoised, divided into frames, and windowed. Then, the time-domain feature short-term energy, short-term zero-crossing rate and frequency domain feature short-term information entropy of each frame of the sound signal are calculated, and double thresholds are set for detection. In this way, the start and end points of the explosion sound in the collected sound signal are found, and the data is imported into the positioning algorithm for processing, and then the explosion point of the weather modification bombs in the high air is located. The test results show that the method can accurately distinguish the end point of effective explosion sound, and has practical application value for the location of the sound source of the high-altitude explosion point of the weather modification bombs.

Purging of silence for robust speaker identification in colossal database

The aim of this work is to develop an effective speaker recognition system under noisy environments for large data sets. The important phases involved in typical identification systems are feature extraction, training and testing. During the feature extraction phase, the speaker-specific information is processed based on the characteristics of the voice signal. Effective methods have been proposed for the silence removal in order to achieve accurate recognition under noisy environments in this work. Pitch and Pitch-strength parameters are extracted as distinct features from the input speech spectrum. Multi-linear principle component analysis (MPCA) is is utilized to minimize the complexity of the parameter matrix. Silence removal using zero crossing rate (ZCR) and endpoint detection algorithm (EDA) methods are applied on the source utterance during the feature extraction phase. These features are useful in later classification phase, where the identification is made on the basis of support vector machine (SVM) algorithms. Forward loking schostic (FOLOS) is the efficient large-scale SVM algorithm that has been employed for the effective classification among speakers. The evaluation findings indicate that the methods suggested increase the performance for large amounts of data in noise ecosystems.

English spoken stress recognition based on natural language processing and endpoint detection algorithm

Nowadays, there are more and more researches on the application of natural language processing technology in computer-aided language system, which can provide a good assistant role for foreign language learners. However, in the research of computer-aided language system, there are still some deficiencies in the recognition of English spoken stress nodes, which cannot be well recognized. Based on this, this paper proposes a method of English spoken accent recognition based on natural language processing and endpoint detection algorithm, which aims to promote the accuracy of accent recognition in the computer-aided language system and improve the performance of the computer-aided language system. In order to avoid the interference of background noise, this paper proposes a short-term time-frequency endpoint detection algorithm which can accurately judge the beginning and end of speech in complex environment. Then, on the basis of traditional speech feature extraction and fractal dimension theory, a nonlinear fractal dimension speech feature is extracted. Finally, RankNet is used to process the extracted features to realize the recognition of English spoken stress nodes. In the simulation analysis, the application effect of the short-term time-frequency endpoint detection algorithm proposed in this paper in the complex background noise and the effect of non-linear fractal dimension speech features on the recognition of English spoken stress nodes are verified. Finally, the performance and good application effect of the method designed in this paper are illustrated.

Research Status and Future Development of Endpoint Detection Algorithms Based on Computer Science Language Signals

Today is an information technology era, language signal recognition technology, language signal coding technology and a variety of new language technology will be widely used in all areas of our life, such as: security field, human-computer interaction, communication field. We can accurately analyze pure speech signals and silent segments in a speech by using language signal endpoint detection technology, which will bring decisive effects to the efficiency of ASR and ASC. Three steps can be used to represent the language endpoint detection model, namely, the language signal preprocessing step, the extraction of the characteristic vector of the whole language flow, and the establishment of the language endpoint discrimination model. Finally, the speech endpoint discrimination model is established. The traditional speech endpoint detection algorithms include the two threshold method based on time domain, the universal entropy method based on frequency domain and the invert characteristic method. Aiming at the low SNR and complex noise environment, in order to obtain satisfactory endpoint detection effect, this paper proposes an endpoint detection model based on optimized Extreme Learning machine (ELM), and makes up for the deficiencies of the algorithm itself by optimizing network connection parameters[1-2].

Optimization of Intelligent Tuning System for Stringed Instruments Based on Wireless Sensor Network

With the increasing abundance of material civilization, people’s pursuit of spiritual civilization is also higher and higher. Although tuning is the analysis and processing of sound signal, the string signal is also a kind of sound signal, which follows the basic law of acoustics. In the field of wireless sensor network, this paper introduces the status quo of tuning tools for stringed instruments, analyses the existing problems of tuning tools for mainstream stringed instruments, and puts forward an automatic tuning system based on wireless sensor network. The hardware design of intelligent tuning system based on wireless sensor network includes audio acquisition module, tuning control module driver circuit design and voice broadcast module, and network communication module selection analysis. The software design of intelligent tuning system based on wireless sensor network includes embedded software design and mobile software design. Embedded software design mainly includes system flow design and automatic tuning function design. In this paper, an improved endpoint detection algorithm is used to separate the chord tone from the nonchord tone, and an improved pitch detection algorithm is used to get the accurate pitch frequency of the chord tone signal. The function and performance of the tuning system are tested to verify the reliability of the optimized intelligent tuning system.