scholarly journals Speech recognition system for Turkish language with hybrid method

2017 ◽  
Vol 7 (1) ◽  
pp. 48-57
Author(s):  
Cigdem Bakir
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Speech Recognition ◽  
Hybrid Model ◽  
Recognition System ◽  
Second Phase ◽  
Speech Recognition System ◽  
Feature Vectors ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Currently, technological developments are accompanied by a number of associated problems. Security takes the first place amongst such problems. In particular, biometric systems such as authentication constitute a significant fraction of the security problem. This is because sound recordings having connection with various crimes are required to be analysed for forensic purposes. Authentication systems necessitate transmission, design and classification of biometric data in a secure manner. The aim of this study is to actualise an automatic voice and speech recognition system using wavelet transform, taking Turkish sound forms and properties into consideration. Approximately 3740 Turkish voice samples of words and clauses of differing lengths were collected from 25 males and 25 females. The features of these voice samples were obtained using Mel-frequency cepstral coefficients (MFCCs), Mel-frequency discrete wavelet coefficients (MFDWCs) and linear prediction cepstral coefficient (LPCC). Feature vectors of the voice samples obtained were trained with k-means, artificial neural network (ANN) and hybrid model. The hybrid model was formed by combining with k-means clustering and ANN. In the first phase of this model, k-means performed subsets obtained with voice feature vectors. In the second phase, a set of training and tests were formed from these sub-clusters. Thus, for being trained more suitable data by clustering increased the accuracy. In the test phase, the owner of a given voice sample was identified by taking the trained voice samples into consideration. The results and performance of the algorithms used for classification are also demonstrated in a comparative manner. Keywords: Speech recognition, hybrid model, k-means, artificial neural network (ANN).

scholarly journals An Critical Analysis of Speech Recognition of Tamil and Malay Language Through Artificial Neural Network

2021 ◽  
Author(s):  
Kingston Pal Thamburaj ◽  
Kartheges Ponniah ◽  
Ilangkumaran Sivanathan ◽  
Muniisvaran Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Speech Recognition ◽  
Data Entry ◽  
Recognition System ◽  
Visual Speech ◽  
Document Preparation ◽  
Multiple Sensors ◽  
Visual Speech Recognition ◽  
Artificial Neural

Human and Computer interaction has been a part of our day-to-day life. Speech is one of the essential and comfortable ways of interacting through devices as well as a human being. The device, particularly smartphones have multiple sensors in camera and microphone, etc. speech recognition is the process of converting the acoustic signal to a smartphone as a set of words. The efficient performance of the speech recognition system highly enhances the interaction between humans and machines by making the latter more receptive to user needs. The recognized words can be applied for many applications such as Commands & Control, Data entry, and Document preparation. This research paper highlights speech recognition through ANN (Artificial Neural Network). Also, a hybrid model is proposed for audio-visual speech recognition of the Tamil and Malay language through SOM (Self-organizing map0 and MLP (Multilayer Perceptron). The Effectiveness of the different models of NN (Neural Network) utilized in speech recognition will be examined.

Acoustic Modeling of Speech Signal using Artificial Neural Network

2016 ◽  
pp. 196-212
Author(s):  
Mousmita Sarma ◽  
Kandarpa Kumar Sarma
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Speech Recognition ◽  
Speech Signal ◽  
Acoustic Modeling ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Sound Unit ◽  
Asr System

Acoustic modeling of the sound unit is a crucial component of Automatic Speech Recognition (ASR) system. This is the process of establishing statistical representations for the feature vector sequences for a particular sound unit so that a classifier for the entire sound unit used in the ASR system can be designed. Current ASR systems use Hidden Markov Model (HMM) to deal with temporal variability and Gaussian Mixture Model (GMM) for acoustic modeling. Recently machine learning paradigms have been explored for application in speech recognition domain. In this regard, Multi Layer Perception (MLP), Recurrent Neural Network (RNN) etc. are extensively used. Artificial Neural Network (ANN)s are trained by back propagating the error derivatives and therefore have the potential to learn much better models of nonlinear data. Recently, Deep Neural Network (DNN)s with many hidden layer have been up voted by the researchers and have been accepted to be suitable for speech signal modeling. In this chapter various techniques and works on the ANN based acoustic modeling are described.

Acoustic Modeling of Speech Signal using Artificial Neural Network

2015 ◽  
pp. 282-299 ◽  
Author(s):  
Mousmita Sarma ◽  
Kandarpa Kumar Sarma
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Speech Recognition ◽  
Speech Signal ◽  
Acoustic Modeling ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Sound Unit ◽  
Asr System

Acoustic modeling of the sound unit is a crucial component of Automatic Speech Recognition (ASR) system. This is the process of establishing statistical representations for the feature vector sequences for a particular sound unit so that a classifier for the entire sound unit used in the ASR system can be designed. Current ASR systems use Hidden Markov Model (HMM) to deal with temporal variability and Gaussian Mixture Model (GMM) for acoustic modeling. Recently machine learning paradigms have been explored for application in speech recognition domain. In this regard, Multi Layer Perception (MLP), Recurrent Neural Network (RNN) etc. are extensively used. Artificial Neural Network (ANN)s are trained by back propagating the error derivatives and therefore have the potential to learn much better models of nonlinear data. Recently, Deep Neural Network (DNN)s with many hidden layer have been up voted by the researchers and have been accepted to be suitable for speech signal modeling. In this chapter various techniques and works on the ANN based acoustic modeling are described.

scholarly journals Automotive Start–Stop Engine Based on Fingerprint Recognition System

2019 ◽  
Vol 130 ◽  
pp. 01022
Author(s):  
Pranoko Rivandi ◽  
Astuti Winda ◽  
Dewanto Satrio ◽  
Mahmud Iwan Solihin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Recognition System ◽  
Security System ◽  
Fingerprint Recognition ◽  
Identification System ◽  
Minutiae Extraction ◽  
Artificial Neural ◽  
The Difference ◽  
Artificial Neural Network Ann

Automated vehicle security system plays an important rule in nowadays advance automotive technology. One of the methods which can be applied for a security system is based on biometric identification system. Fingerprint recognition is one of the biometric systems that can be applied to the security system. In this work, fingerprint recognition system to start the motorcycle engine is developed. The fingerprint of the owner and other authorized persons will be stored into the database, then while the time of starting the engine of the vehicle, the fingerprint will be validated with the database. The minutiae extraction method is applied to find the difference of fingerprint each other after turn the image into grayscale and thinning. After the extraction, the next step is finding the ridge edge and bifurcation. The result of the image will be used as input to the Artificial Neural Network (ANN) to recognize authorized person only. The experiment of fingerprint recognition system shows that automatic start-stop engine using fingerprint recognition system based minutiae extraction and Artificial Neural Network (ANN) has accuracy 100 % and 100 %, respectively.

scholarly journals Footstep Recognition Using Mel Frequency Cepstral Coefficients and Artificial Neural Network

2020 ◽  
Vol 4 (3) ◽  
pp. 497-503
Author(s):  
Thasya Nurul Wulandari Siagian ◽  
Hilal Hudan Nuha ◽  
Rahmat Yasirandi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Recognition System ◽  
Error Rates ◽  
Mel Frequency Cepstral Coefficients ◽  
Security Systems ◽  
Artificial Neural ◽  
Cepstral Coefficients ◽  
Human Hearing ◽  
Artificial Neural Network Ann

Footstep recognition is relatively new biometrics and based on the learning of footsteps signals captured from people walking on the sensing area. The footstep signals classification process for security systems still has a low level of accuracy. Therefore, we need a classification system that has a high accuracy for security systems. Most systems are generally developed using geometric and holistic features but still provide high error rates. In this research, a new system is proposed by using the Mel Frequency Cepstral Coefficients (MFCCs) feature extraction, because it has a good linear frequency as a copycat of the human hearing system and Artificial Neural Network (ANN) as a classification algorithm because it has a good level of accuracy with a dataset of 500 recording footsteps. The classification results show that the proposed system can achieve the highest accuracy of validation loss value 57.3, Accuracy testing 92.0%, loss value 193.8, and accuracy training 100%, the accuracy results are an evaluation of the system in improving the foot signal recognition system for security systems in the smart home environment.

scholarly journals Using an Artificial Neural Network to Validate and Predict the Physical Properties of Self-Compacting Concrete

2022 ◽  
Vol 2022 ◽  
pp. 1-10
Author(s):  
K. Thirumalai Raja ◽  
N. Jayanthi ◽  
Jule Leta Tesfaye ◽  
N. Nagaprasad ◽  
R. Krishnaraj ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Compressive Strength ◽  
Concrete Strength ◽  
Setting Time ◽  
Second Phase ◽  
Self Compacting Concrete ◽  
Initial Setting Time ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

SCC (self-compacting concrete) is a high-flowing concrete that blasts into structures. Many academics have been interested in using an artificial neural network (ANN) to forecast concrete strength in recent years. As a result, the goal of this study is to confirm the various possibilities of using an artificial neural network (ANN) to detect the features of SCC when Portland Pozzolana Cement (PPC) is partially substituted with biowaste such as Bagasse Ash (BA) and Rice Husk Ash (RHA) (RHA). Specialist systems based on the fully connected cascade (FCC) architecture in artificial neural networks (ANN) are used to estimate the compressive toughness of SCC. The research results are confirmed with the forecasting results of ANN utilizing 73 trial datasets of differentiation focus proposals of cement, BA, and RHA containing parameters such as initial setting time (IST), final setting time (FST), and standard consistency. Experiments to determine compressive strength for a wider range of mixed prepositions will result in higher project expenses and delays. So, an expert system ANN is used to find the standard consistency, setting time, and compressive strength for the intermediate mix propositions according to IS 10262:2009. The experimental results of compressive strength for 28 days are considered, in which 70% was used to train the ANN and 30% was utilized for testing the accuracy of the predicted compressive strength for the intermediate mix proposition. Using all of the datasets, the number of hidden layers used for compressive strength prediction for intermediate mix proposal is determined in the first step. The compressive strength for the intermediate mix preposition was identified in the second phase of the research, using the number of hidden layers determined in the first phase. The results were validated using the correlation coefficient (R) and root mean square error (RMSE) obtained from ANN, resulting in an acceptance range of 97 percent to 99 percent.

Sign in / Sign up

Export Citation Format

Share Document