Speech is the most familiar and habitual way of communication used by most of us. Due to speech d... more Speech is the most familiar and habitual way of communication used by most of us. Due to speech disabilities, many people find it difficult to properly voice their views and thus are at a disadvantage. The re- search tackles the issue of lack of speech from a speech impaired user by recognizing it with the use of ML models such as Gaussian Mixture Model - GMM and Convolutional Neural Network - CNN. With properly recorded and cleaned muscle activity from the facial muscles it is possi- ble to predict the words being uttered/whispered with a certain accuracy. The intended system will additionally also have a visual aid system which can provide better accuracy when used together with the facial muscle activity-based system. Neuromuscular signals from the speech articulat- ing muscles are recorded using Surface ElectroMyoGraphy (SEMG) sen- sors, which will be used to train the machine learning models. In this paper we have demonstrated various signals synthesized through the ElectroMyograp...
2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC), 2016
Recognition of speech with the help of machine automatically is an important area of research for... more Recognition of speech with the help of machine automatically is an important area of research for more than forty years. As Voice is a signal of limitless information, so processing of speech signal by converting into digital is very efficient tool for high and precise automatic signal or voice recognition technology. Speech recognition has found its application in various areas of our daily lives as automatic answering machine to convey text and issue voice signal for the machines. Feature Extraction and Classification are main processing part of ASR system. The main part for the speech processing system to improve capability is the selection of Feature Extraction method which plays an important role in the system precision. This paper gives brief overview on the survey of various methods in speech processing such as ‘Wavelet Transform’ and ‘Soft Computing Techniques’ as ANN, HMM and GMM for isolated digit recognition.
Speech recognition applications are becoming more and more practical nowadays. Various interactiv... more Speech recognition applications are becoming more and more practical nowadays. Various interactive speech aware applications are available in the market. But they are usually meant for and executed on the traditional general-purpose computers. Due to the rapid technological advancements, bigger and more complex tasks are being efficiently performed consuming less time and efforts. This can be further simplified with a more hands-free approach with the help of Voice Controlled System. For implementing this, we use an open source platform called Jasper for Raspberry Pi. Our aim is to build an automated personal secretary who could remind us of our schedule and optimize the rudimentary ways of performing tasks at one's commands.
2018 3rd International Conference On Internet of Things: Smart Innovation and Usages (IoT-SIU), 2018
Speech processing systems are actively considered for voice recognition, control and communicatio... more Speech processing systems are actively considered for voice recognition, control and communication systems due to tremendous improvement in the digital signal processor and digital programmable logic devices. Preprocessing, feature extraction and classification are the fundamental steps involved in speech processing systems. Mostly transform domain and soft computing techniques are employed for feature extraction and classification respectively. Low computational complexity is desired to make speech processing systems as commercially viable solution. In this paper, speech recognition system for Marathi digit recognition using discrete wavelet transform (DWT), reduced order LPC coefficient and ANN is proposed. The main objective was to estimate the performance ofthe speech processing system at minimum feature vector length without significantly sacrificing on recognition rate. Better representation of speech frame was obtained using LPC coefficients derived from discrete wavelet-decomposed subbands instead of modeling the frame directly. Artificial neural network was used in the implementation of speech recognition system as classifier. An experimental result on Marathi digits from one to nine has demonstrated 78 % of the recognition rate at the minimum feature vector length of 24.
This paper presents a brief survey on Wireless sensor networks with emphasis on their application... more This paper presents a brief survey on Wireless sensor networks with emphasis on their application in security systems. The design of Wireless Sensor Network (WSN) security systems requires special attention to a number of parameters such as secure routing algorithms, power constraints, accuracy and quality of service. This paper discusses components of wireless sensor networks: sensors, processors; and compares various solutions available. This paper also looks at some of the methods of communication within the network. The objective of this review is to summarize and compare some of the well known methods used in various stages of WSN design.
2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017
Deblurring is the process of removing blurring artifacts from signals, such as blur caused by noi... more Deblurring is the process of removing blurring artifacts from signals, such as blur caused by noise, defocus aberration or motion blur. Blind Convolution for signal separation is an area of research in the field of signal processing from last few decades. Similarly, image deblurring and restoration has also been an area of research using different techniques like Blind Signal Separation (BSS), Singular Value Decomposition (SVD) combined with DCT, DWT, Differential Evolution Optimization. However, very little research is been done on audio deblurring. In this paper, we proposed an idea for deblurring of an audio signal using SVD. At the end, we also computed root mean square error (RMSE), normalized root mean square error (NRMSE) and peak signal-to-noise ratio (PSNR) between the original audio signals and the signals retrieved after applying SVD.
International Journal of Innovative Research in Computer and Communication Engineering, 2013
Speech has been embedded into many applications like speech recognition, development of hearing a... more Speech has been embedded into many applications like speech recognition, development of hearing aid, VoIP, mobile and other forms of personal communication. Speech enhancement techniques have been widely used for minimizing undesirable background noises. This paper deals with single channel speech enhancement techniques based on Spectral Subtraction (SS), Wavelet Transform (WT) and Adaptive Wiener Filtering (AWF). Here quantitative performance of these speech enhancement techniques is compared and the parameters used for comparison are Mean Square Error, Normalised Mean Square Error, Signal to Noise Ratio, Peak Signal to Noise Ratio and Average Absolute Distortion. The results obtained have proved the speech enhancing capability of the personal communication technique where noise and echo-interference can degrade the original speech signal. From the results we conclude that the performance of single channel speech enhancement based WT is better than AWF and SS techniques. MATLAB GUI...
Speech recognition with the help of the machine is automatically an important research area for o... more Speech recognition with the help of the machine is automatically an important research area for over forty years. Since the voice is an unlimited information signal, the speech signal processing through digital conversion is a very efficient tool for high and accurate automatic signal or voice recognition technology. Speech recognition has found its application in different areas of our daily life as a telephone answering machine for transmitting text and sending voice signals to machines. Function extraction and classification is a major part of the ASR system process. The main part of the voice processing system to improve capacity is the selection of the function extraction method that plays an important role in the accuracy of the system. This document provides a brief overview of the detection of various methods in speech processing where DCT uses to efficiently extract features in different ways.
96 Abstract— The speech based applications have been always important in communication for the hu... more 96 Abstract— The speech based applications have been always important in communication for the humans. There are in various essential applications like speech recognition, voice-distance-talk and other forms of personal communications. Most recently, speech based interface has been tried to be employed in almost all the mobile and stationary devices. However, these attempts could not give ultimate response due to variations in surrounding noises, changes in person to person speech and also intra person variation. This scenario leads to further research that will make speech recognition more robust and general and can be applied upcoming electronic devices to be sued for gaming, entertainment, cellular phones. The broad categories of speech enhancement techniques can be listed as speech filtering techniques, beam forming techniques and active noise cancellation methods. In this paper, we have improved the performance of beamforming based speech recognition system using evolutionary c...
2018 3rd International Conference for Convergence in Technology (I2CT), 2018
Tremendous development in the digital technology has necessitated the copyright protection and au... more Tremendous development in the digital technology has necessitated the copyright protection and authentication of the images, audios, video and documents using watermarking techniques. Audio watermarking is more challenging due to the fact that dynamic supremacy of hearing capacity over the visual field. Encryption of the watermark signal or image enhances its security under malicious attacks through high entropy. In this paper, performance of the proposed audio encryption algorithm using modified elliptical curve cryptography and Arnold transform is evaluated to determine its suitability for audio watermarking techniques. Elliptical curve cryptography benefits from smaller key size and large key space without sacrificing on level of security. Arnold transform is commonly employed in two dimensional domains for scattering of the pixels in an image. Single dimensional audio signal was converted into two dimensional signals before applying Arnold transform through elliptical curve cryp...
This paper presents a brief survey on Wireless sensor networks with emphasis on their application... more This paper presents a brief survey on Wireless sensor networks with emphasis on their application in security systems. The design of Wireless Sensor Network (WSN) security systems requires special attention to a number of parameters such as secure routing algorithms, power constraints, accuracy and quality of service. This paper discusses components of wireless sensor networks: sensors, processors; and compares various solutions available. This paper also looks at some of the methods of communication within the network. The objective of this review is to summarize and compare some of the well known methods used in various stages of WSN design.
Speech is the fundamental, most effective, reliable and common medium to communicate in real time... more Speech is the fundamental, most effective, reliable and common medium to communicate in real time systems. There are so many applications of speech still to be far from reality just because of lack of efficient and reliable noise removal mechanism and techniques for preserving or improving the intelligibility for the speech signals. In this paper attempt has been stepped towards surveying the methodologies for soft computing based speech recognition techniques for speech enhancement in multimedia applications. Finally we can conclude that to improve the performance of beamforming based speech recognition system, evolutionary computational algorithm (GA) optimization can be used in multimedia applications.
Digital audio watermarking is very popular in recent research area, watermarking is a method to h... more Digital audio watermarking is very popular in recent research area, watermarking is a method to hide information signal into digital form based on spread spectrum, The identity of the owner of the audio file can be invisible in the audio file which is called Watermark Therefore, digital audio watermarking is the process in which whole data into the audio file in such a way that the audibility of the audio is not affected. In this paper, various methods of audio-watermarking have been discussed, which is used to protect right owner by using watermark as a part of that audio, image and video data to eliminate watermark from data is very difficult if someone copied information so watermark also carried with copy and data can carry various authentication etc.
Speech is the most familiar and habitual way of communication used by most of us. Due to speech d... more Speech is the most familiar and habitual way of communication used by most of us. Due to speech disabilities, many people find it difficult to properly voice their views and thus are at a disadvantage. The re- search tackles the issue of lack of speech from a speech impaired user by recognizing it with the use of ML models such as Gaussian Mixture Model - GMM and Convolutional Neural Network - CNN. With properly recorded and cleaned muscle activity from the facial muscles it is possi- ble to predict the words being uttered/whispered with a certain accuracy. The intended system will additionally also have a visual aid system which can provide better accuracy when used together with the facial muscle activity-based system. Neuromuscular signals from the speech articulat- ing muscles are recorded using Surface ElectroMyoGraphy (SEMG) sen- sors, which will be used to train the machine learning models. In this paper we have demonstrated various signals synthesized through the ElectroMyograp...
2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC), 2016
Recognition of speech with the help of machine automatically is an important area of research for... more Recognition of speech with the help of machine automatically is an important area of research for more than forty years. As Voice is a signal of limitless information, so processing of speech signal by converting into digital is very efficient tool for high and precise automatic signal or voice recognition technology. Speech recognition has found its application in various areas of our daily lives as automatic answering machine to convey text and issue voice signal for the machines. Feature Extraction and Classification are main processing part of ASR system. The main part for the speech processing system to improve capability is the selection of Feature Extraction method which plays an important role in the system precision. This paper gives brief overview on the survey of various methods in speech processing such as ‘Wavelet Transform’ and ‘Soft Computing Techniques’ as ANN, HMM and GMM for isolated digit recognition.
Speech recognition applications are becoming more and more practical nowadays. Various interactiv... more Speech recognition applications are becoming more and more practical nowadays. Various interactive speech aware applications are available in the market. But they are usually meant for and executed on the traditional general-purpose computers. Due to the rapid technological advancements, bigger and more complex tasks are being efficiently performed consuming less time and efforts. This can be further simplified with a more hands-free approach with the help of Voice Controlled System. For implementing this, we use an open source platform called Jasper for Raspberry Pi. Our aim is to build an automated personal secretary who could remind us of our schedule and optimize the rudimentary ways of performing tasks at one's commands.
2018 3rd International Conference On Internet of Things: Smart Innovation and Usages (IoT-SIU), 2018
Speech processing systems are actively considered for voice recognition, control and communicatio... more Speech processing systems are actively considered for voice recognition, control and communication systems due to tremendous improvement in the digital signal processor and digital programmable logic devices. Preprocessing, feature extraction and classification are the fundamental steps involved in speech processing systems. Mostly transform domain and soft computing techniques are employed for feature extraction and classification respectively. Low computational complexity is desired to make speech processing systems as commercially viable solution. In this paper, speech recognition system for Marathi digit recognition using discrete wavelet transform (DWT), reduced order LPC coefficient and ANN is proposed. The main objective was to estimate the performance ofthe speech processing system at minimum feature vector length without significantly sacrificing on recognition rate. Better representation of speech frame was obtained using LPC coefficients derived from discrete wavelet-decomposed subbands instead of modeling the frame directly. Artificial neural network was used in the implementation of speech recognition system as classifier. An experimental result on Marathi digits from one to nine has demonstrated 78 % of the recognition rate at the minimum feature vector length of 24.
This paper presents a brief survey on Wireless sensor networks with emphasis on their application... more This paper presents a brief survey on Wireless sensor networks with emphasis on their application in security systems. The design of Wireless Sensor Network (WSN) security systems requires special attention to a number of parameters such as secure routing algorithms, power constraints, accuracy and quality of service. This paper discusses components of wireless sensor networks: sensors, processors; and compares various solutions available. This paper also looks at some of the methods of communication within the network. The objective of this review is to summarize and compare some of the well known methods used in various stages of WSN design.
2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017
Deblurring is the process of removing blurring artifacts from signals, such as blur caused by noi... more Deblurring is the process of removing blurring artifacts from signals, such as blur caused by noise, defocus aberration or motion blur. Blind Convolution for signal separation is an area of research in the field of signal processing from last few decades. Similarly, image deblurring and restoration has also been an area of research using different techniques like Blind Signal Separation (BSS), Singular Value Decomposition (SVD) combined with DCT, DWT, Differential Evolution Optimization. However, very little research is been done on audio deblurring. In this paper, we proposed an idea for deblurring of an audio signal using SVD. At the end, we also computed root mean square error (RMSE), normalized root mean square error (NRMSE) and peak signal-to-noise ratio (PSNR) between the original audio signals and the signals retrieved after applying SVD.
International Journal of Innovative Research in Computer and Communication Engineering, 2013
Speech has been embedded into many applications like speech recognition, development of hearing a... more Speech has been embedded into many applications like speech recognition, development of hearing aid, VoIP, mobile and other forms of personal communication. Speech enhancement techniques have been widely used for minimizing undesirable background noises. This paper deals with single channel speech enhancement techniques based on Spectral Subtraction (SS), Wavelet Transform (WT) and Adaptive Wiener Filtering (AWF). Here quantitative performance of these speech enhancement techniques is compared and the parameters used for comparison are Mean Square Error, Normalised Mean Square Error, Signal to Noise Ratio, Peak Signal to Noise Ratio and Average Absolute Distortion. The results obtained have proved the speech enhancing capability of the personal communication technique where noise and echo-interference can degrade the original speech signal. From the results we conclude that the performance of single channel speech enhancement based WT is better than AWF and SS techniques. MATLAB GUI...
Speech recognition with the help of the machine is automatically an important research area for o... more Speech recognition with the help of the machine is automatically an important research area for over forty years. Since the voice is an unlimited information signal, the speech signal processing through digital conversion is a very efficient tool for high and accurate automatic signal or voice recognition technology. Speech recognition has found its application in different areas of our daily life as a telephone answering machine for transmitting text and sending voice signals to machines. Function extraction and classification is a major part of the ASR system process. The main part of the voice processing system to improve capacity is the selection of the function extraction method that plays an important role in the accuracy of the system. This document provides a brief overview of the detection of various methods in speech processing where DCT uses to efficiently extract features in different ways.
96 Abstract— The speech based applications have been always important in communication for the hu... more 96 Abstract— The speech based applications have been always important in communication for the humans. There are in various essential applications like speech recognition, voice-distance-talk and other forms of personal communications. Most recently, speech based interface has been tried to be employed in almost all the mobile and stationary devices. However, these attempts could not give ultimate response due to variations in surrounding noises, changes in person to person speech and also intra person variation. This scenario leads to further research that will make speech recognition more robust and general and can be applied upcoming electronic devices to be sued for gaming, entertainment, cellular phones. The broad categories of speech enhancement techniques can be listed as speech filtering techniques, beam forming techniques and active noise cancellation methods. In this paper, we have improved the performance of beamforming based speech recognition system using evolutionary c...
2018 3rd International Conference for Convergence in Technology (I2CT), 2018
Tremendous development in the digital technology has necessitated the copyright protection and au... more Tremendous development in the digital technology has necessitated the copyright protection and authentication of the images, audios, video and documents using watermarking techniques. Audio watermarking is more challenging due to the fact that dynamic supremacy of hearing capacity over the visual field. Encryption of the watermark signal or image enhances its security under malicious attacks through high entropy. In this paper, performance of the proposed audio encryption algorithm using modified elliptical curve cryptography and Arnold transform is evaluated to determine its suitability for audio watermarking techniques. Elliptical curve cryptography benefits from smaller key size and large key space without sacrificing on level of security. Arnold transform is commonly employed in two dimensional domains for scattering of the pixels in an image. Single dimensional audio signal was converted into two dimensional signals before applying Arnold transform through elliptical curve cryp...
This paper presents a brief survey on Wireless sensor networks with emphasis on their application... more This paper presents a brief survey on Wireless sensor networks with emphasis on their application in security systems. The design of Wireless Sensor Network (WSN) security systems requires special attention to a number of parameters such as secure routing algorithms, power constraints, accuracy and quality of service. This paper discusses components of wireless sensor networks: sensors, processors; and compares various solutions available. This paper also looks at some of the methods of communication within the network. The objective of this review is to summarize and compare some of the well known methods used in various stages of WSN design.
Speech is the fundamental, most effective, reliable and common medium to communicate in real time... more Speech is the fundamental, most effective, reliable and common medium to communicate in real time systems. There are so many applications of speech still to be far from reality just because of lack of efficient and reliable noise removal mechanism and techniques for preserving or improving the intelligibility for the speech signals. In this paper attempt has been stepped towards surveying the methodologies for soft computing based speech recognition techniques for speech enhancement in multimedia applications. Finally we can conclude that to improve the performance of beamforming based speech recognition system, evolutionary computational algorithm (GA) optimization can be used in multimedia applications.
Digital audio watermarking is very popular in recent research area, watermarking is a method to h... more Digital audio watermarking is very popular in recent research area, watermarking is a method to hide information signal into digital form based on spread spectrum, The identity of the owner of the audio file can be invisible in the audio file which is called Watermark Therefore, digital audio watermarking is the process in which whole data into the audio file in such a way that the audibility of the audio is not affected. In this paper, various methods of audio-watermarking have been discussed, which is used to protect right owner by using watermark as a part of that audio, image and video data to eliminate watermark from data is very difficult if someone copied information so watermark also carried with copy and data can carry various authentication etc.
Uploads