Speech Signal Feature Extraction Research Articles

Feature Extraction of Speech Signal Based on MFCC (Mel cepstrum coefficient)

Smart power plant is to establish a modern energy power system to achieve safe, efficient, green, and low-carbon power generation. Its characteristics are that the production process can be independently optimized, the relevant systems can collect, analyze, judge, and plan their own behavior, and intelligently and dynamically optimize equipment configuration and its parameters. This paper focuses on the optimal recognition state of MFCC in smart power plants. In this paper, we propose that by changing the number of filters and the order of MFCC to view the expression effect of the final MFCC parameter, the evaluation index of the effect is “accuracy”, the evaluation index—accuracy in the neural network. In this paper, the network is built through a Python programming environment, and the comparative experiment is adopted to analyze the influence of each parameter on the speech information expression effect of MFCC parameters.

Individual Identification Through Voice Using Mel-Frequency Cepstrum Coefficient (MFCC) and Hidden Markov Models (HMM) Method

Voice is one of the parameters in the identification process of a person. Through the voice, information will be obtained such as gender, age, and even the identity of the speaker. Speaker recognition is a method to narrow down crimes and frauds committed by voice. So that it will minimize the occurrence of faking one's identity. The Method of Mel Frequency Cepstrum Coefficient (MFCC) can be used in the speech recognition system. The process of feature extraction of speech signal using MFCC will produce acoustic speech signal. The classification, Hidden Markov Models (HMM) is used to match unidentified speaker’s voice with the voices in database. In this research, the system is used to verify the speaker, namely 15 text dependent in Indonesian. On testing the speaker with the same as database, the highest accuracy is 99,16%.

Optimization of Computer Aided English Pronunciation Teaching System Based on Speech Signal Processing Technology

After the development of speech signal processing technology has matured, various language learning tools have begun to emerge. The speech signal processing technology has many functions, such as standard tape reading, making audio aids, synthesizing speech, and performing speech evaluation. Therefore, the adoption of speech signal processing technology in English pronunciation teaching can meet different teaching needs. Voice signal processing technology can present teaching information in different forms, and promote multi-form communication between teachers and students, and between students and students. This will help stimulate students' interest in learning English and improve the overall teaching level of English pronunciation. This research first investigates and studies the current level of English pronunciation mastery. After combining the relevant principles of speech signal processing technology, it puts forward the areas that need to be optimized in the design of the English pronunciation teaching system. Through the demand analysis and function analysis of the system, this research uses speech signal processing technology to extract the characteristics of the speech signal---Mel Frequency Cepstrum Coefficient (MFCC), The system's speech signal preprocessing, speech signal feature extraction and dynamic time warping (DTW) recognition algorithms are optimized. At the same time, this research combines multimedia teaching resources such as text, pronunciation video and excellent courses to study the realization process of each function of the system.

Voice Control System Based on Zynq FPGA

In this paper, a speech recognition system is designed and the relevant hard-ware environment is built through Zynq FPGA AX7020 platform. In this system, the feature extraction of speech signals is based on MFCC (mel-frequency cepstrum coefficients). The algorithm in this system includes Pre-emphasis, Framing and Windowing, FFT, MFCC Parameter Calculation, VED Endpoint Detection and DTW Operations processes commonly used in speech system design. In this paper, the speech recognition algorithm is implemented on Zynq FPGA platform and also simulated in Matlab. At the same time, audio module AN831 is adopted in the hardware part to realize the sound acquisition function. Through the comparison of experimental data, it is found that the average recognition rate in Matlab simulation is 86.67%, while in Zynq FPGA platform test, the recognition rate is 80.67%. Using Zynq FPGA AX7020 as a platform to realize speech recognition, the recognition rate is higher than the traditional speech recognition technology.

Unsupervised speech recognition through spike-timing-dependent plasticity in a convolutional spiking neural network.

Speech recognition (SR) has been improved significantly by artificial neural networks (ANNs), but ANNs have the drawbacks of biologically implausibility and excessive power consumption because of the nonlocal transfer of real-valued errors and weights. While spiking neural networks (SNNs) have the potential to solve these drawbacks of ANNs due to their efficient spike communication and their natural way to utilize kinds of synaptic plasticity rules found in brain for weight modification. However, existing SNN models for SR either had bad performance, or were trained in biologically implausible ways. In this paper, we present a biologically inspired convolutional SNN model for SR. The network adopts the time-to-first-spike coding scheme for fast and efficient information processing. A biological learning rule, spike-timing-dependent plasticity (STDP), is used to adjust the synaptic weights of convolutional neurons to form receptive fields in an unsupervised way. In the convolutional structure, the strategy of local weight sharing is introduced and could lead to better feature extraction of speech signals than global weight sharing. We first evaluated the SNN model with a linear support vector machine (SVM) on the TIDIGITS dataset and it got the performance of 97.5%, comparable to the best results of ANNs. Deep analysis on network outputs showed that, not only are the output data more linearly separable, but they also have fewer dimensions and become sparse. To further confirm the validity of our model, we trained it on a more difficult recognition task based on the TIMIT dataset, and it got a high performance of 93.8%. Moreover, a linear spike-based classifier—tempotron—can also achieve high accuracies very close to that of SVM on both the two tasks. These demonstrate that an STDP-based convolutional SNN model equipped with local weight sharing and temporal coding is capable of solving the SR task accurately and efficiently.

The Implementation of Speech Recognition using Mel-Frequency Cepstrum Coefficients (MFCC) and Support Vector Machine (SVM) method based on Python to Control Robot Arm

In this paper describe an implementation of speech recognition to pick and place an object using Robot Arm. To get the feature extraction of speech signal used Mel-Frequency Cepstrum Coefficients (MFCC) method and to learn the database of speech recognition used Support Vector Machine (SVM) method, the algorithm based on Python 2.7. The data learning which used to SVM process are 12 features, then the system tested using trained and not trained data show the best agreement to identifying the speech recognition. The speech recognition system has been implemented for control the 5 DoF Robot Arm based Arduino microcontroller to doing task pick and place the object.

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN.

Accurate emotion recognition from speech is important for applications like smart health care, smart entertainment, and other smart services. High accuracy emotion recognition from Chinese speech is challenging due to the complexities of the Chinese language. In this paper, we explore how to improve the accuracy of speech emotion recognition, including speech signal feature extraction and emotion classification methods. Five types of features are extracted from a speech sample: mel frequency cepstrum coefficient (MFCC), pitch, formant, short-term zero-crossing rate and short-term energy. By comparing statistical features with deep features extracted by a Deep Belief Network (DBN), we attempt to find the best features to identify the emotion status for speech. We propose a novel classification method that combines DBN and SVM (support vector machine) instead of using only one of them. In addition, a conjugate gradient method is applied to train DBN in order to speed up the training process. Gender-dependent experiments are conducted using an emotional speech database created by the Chinese Academy of Sciences. The results show that DBN features can reflect emotion status better than artificial features, and our new classification approach achieves an accuracy of 95.8%, which is higher than using either DBN or SVM separately. Results also show that DBN can work very well for small training databases if it is properly designed.

Voice Verification System Based on Bark-frequency Cepstral Coefficient

Data verification systems evolve towards a more natural system using biometric media. In daily interactions, human use voice as a tool to communicate with others. Voice charactheristic is also used as a tool to identify subjects who are speaking. The problem is that background noise and signal characteristics of each person which is unique, cause speaker classification process becomes more complex. To identify the speaker, we need to understand the speech signal feature extraction process. We developed the technology to extract voice characteristics of each speaker based on spectral analysis. This research is useful for the development of biometric-based security application. At first, the voice signal will be separated by a pause signal using voice activity detection. Then the voice characteristic will be extracted using a bark-frequency cepstral coefficient. Set of cepstral will be classified according to the speaker, using artificial neural network. The accuracy reached about 82% in voice recognition process with 10 speakers, meanwhile, the highest accuracy was 93% with only 1 speaker.

Feature Extraction of Speech Signal using LPC

Feature Extraction of Speech Signal using LPC

IJARCCE - Computer and Communication Engineering

3 Abstract: A K-Nearest Neighbour Algorithm involving Mel-Frequency Cepstral Coefficients (MFCCs) is provided to perform Speech signal feature extraction for the task of speaker accent recognition. Mel-Frequency Cepstral Co- efficient is effectively used to perform the feature extraction of the input signal. For each input signal the mean of the MFCC matrix is used for pattern recognition .The K-nearest neighbour algorithm is based on evaluating minimum Euclidean distance measure from input data set to stored data set. Since large number of speakers of different accent are present, they can be grouped together depending upon their accent .Thus each signal coming from different group makes a distinct MFCC vector .In this paper we have compared the MFCC from global group to smaller sub groups.

Vehicle Type Recognition in Sensor Networks Using Improved Time Encoded Signal Processing Algorithm

Vehicle type recognition is a demanding application of wireless sensor networks (WSN). In many cases, sensor nodes detect and recognize vehicles from their acoustic or seismic signals using wavelet based or spectral feature extraction methods. Such methods, while providing convincing results, are quite demanding in computational power and energy and are difficult to implement on low-cost sensor nodes with limitation resources. In this paper, we investigate the use of time encoded signal processing (TESP) algorithm for vehicle type recognition. The conventional TESP algorithm, which is effective for the speech signal feature extraction, however, is not suitable for the vehicle sound signal which is more complex. To solve this problem, an improved time encoded signal processing (ITESP) is proposed as the feature extraction method according to the characteristics of the vehicle sound signal. Recognition procedure is accomplished using the support vector machine (SVM) and thek-nearest neighbor (KNN) classifier. The experimental results indicate that the vehicle type recognition system with ITESP features give much better performance compared with the conventional TESP based features.

Speaker age detection using eigen value

In this research an algorithm was suggested for classifying a speaker age to two classes: (young and old classes) based on his speech signal. The suggested algorithm depend on a speech signal feature extraction in order to get a compact representation for this signal and to adopte these features in the classification process. In this algorithm, the eigen values of the covariance matrix was adopted as a principle parameter in the recognition between the two classes. It was constructed from the data of the speech signal (usually one dimension( after rearranghng it into a number (2,4,8,16,32,64) of a two dimension square matrix array . The suggested algorithm include two main stages: • 1st stage: includes data file preparation that contains the eigen values for a number of persons belong to both classes young and old (with different gender), in this stage the average of these values for each class to be calculated separately and the threshold curve(which represents the boundary seperating between two classes( were also computed. Second stage: in this stage the classification process was done by comparing the curve that represents the eigen values of the speech signal, with the threshold curve, a different number of performance parameters are adopted in the evaluation the accuracy of the classification process. The measured correlation value was in range of (0.9610, 0.9994) when m=2 and m=64, respectively (this means whenever the number of arrays that the speech signal constructed from it increases, the correlation coefficient also increases) , while a clear difference can be seen with mmse parameter. After applying the suggested algorithm on 50 persons from both genders, the algorithm passed in applying 80% and failed in percentage 20% of them.

A neural predictive coding feature extraction scheme in DCT domain for phoneme recognition

Nonlinear feature extraction of speech signals has been the main concern of many researches in recent years. In this paper, feature extraction of phonemes using NPC (neural predictive coding) model is generalized to a combination of time and DCT domains. Two main ideas were proposed and evaluated in this paper. First, a frame-wise DCT-based NPC feature extractor is proposed to overcome the computational complexity deficiency of the system. The basis of this approach is the application of a DCT pre-feature extractor to remove unwanted additional data. In this approach, the extracted features are the output of the hidden layer. It is shown that the use of a pre-processing stage can improve both computational complexity efficiency and accuracy issues. At the second approach, we proposed a complementary role for DCT domain features in classic NPC modeling. This approach uses the signal residual of the predicted signal in the DCT domain. The experiments were conducted on voiced plosive phonemes of TIMIT database. Simulations showed that the performance of the combined method is good at the plosive phonemes. The achieved accuracy that was resulted from the proposed method was 70.3% recognition rate on /b/d/g/ phonemes, which is higher than the results of traditional NPC approaches.