Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760851
M. Mikulec, J. Rozhon, M. Voznák
The paper deals with real time round trip measurement methodology. In contrast with probe-based methods, the new methodology tries to use an existing VoIP Operator infrastructure without any hardware or software installation into the infrastructure. The measurement is based on packet payload comparison and timestamp evaluation. The results of the measurement can be used as an external monitoring tool of VoIP infrastructure between VoIP Operators or for call admission control functions.
{"title":"Real time round trip delay time measurement methodology between remote VoIP Operators","authors":"M. Mikulec, J. Rozhon, M. Voznák","doi":"10.1109/TSP.2016.7760851","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760851","url":null,"abstract":"The paper deals with real time round trip measurement methodology. In contrast with probe-based methods, the new methodology tries to use an existing VoIP Operator infrastructure without any hardware or software installation into the infrastructure. The measurement is based on packet payload comparison and timestamp evaluation. The results of the measurement can be used as an external monitoring tool of VoIP infrastructure between VoIP Operators or for call admission control functions.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115971836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760928
Najwa-Maria Chidiac, Pascal Damien, C. Yaacoub
A robust algorithm that detects text from natural scene images and extracts them regardless of the orientation is proposed. All existing methods are designed to operate under a certain constraint, like detecting text only in one direction. Maximally Stable Extremal Regions (MSER) detector is chosen to extract binary regions since it has proven to be robust to lighting conditions. An enhancement technique for MSER images is designed to obtain clear letter boundaries. Images are then fed into a Stroke Width Detector and several heuristics are applied to remove non-text pixels. Afterwards, detected text regions are fed into an Optical Character Recognition module and then filtered according to their confidence measure. The recognition of characters is not part of the algorithm and the results are only about the detection of text. Our algorithm proved to be effective on blurred images and noisy images as well, based on both subjective and objective evaluations.
{"title":"A robust algorithm for text extraction from images","authors":"Najwa-Maria Chidiac, Pascal Damien, C. Yaacoub","doi":"10.1109/TSP.2016.7760928","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760928","url":null,"abstract":"A robust algorithm that detects text from natural scene images and extracts them regardless of the orientation is proposed. All existing methods are designed to operate under a certain constraint, like detecting text only in one direction. Maximally Stable Extremal Regions (MSER) detector is chosen to extract binary regions since it has proven to be robust to lighting conditions. An enhancement technique for MSER images is designed to obtain clear letter boundaries. Images are then fed into a Stroke Width Detector and several heuristics are applied to remove non-text pixels. Afterwards, detected text regions are fed into an Optical Character Recognition module and then filtered according to their confidence measure. The recognition of characters is not part of the algorithm and the results are only about the detection of text. Our algorithm proved to be effective on blurred images and noisy images as well, based on both subjective and objective evaluations.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129161310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760818
I. Bolodurina, D. Parfenov
Data centers are widely used for the placement of highly loaded applications and solutions used for the processing of large data sets (BigData). For effective access to services, minimal response time of data storages is required. We explored a new paradigm in software-defined infrastructure distributed cloud systems. Also the design principles and high-level architectural design of the SD infrastructure controller are presented here. Modern applications and services needs constantly transforming infrastructure for ensuring consumer requirements (SLAs) amidst provider constraints (costs). This paper examines infrastructure in the context of platform for new applications and services and discussing some of the fundamental characteristics required of such infrastructure called software-defined infrastructure (SDI). We developed the models of the software-defined infrastructure. We performed an experiment to analyze the productivity of software-defined storage. Our experiment has shown that software-defined storage and scheduling algorithm in software-defined infrastructure placement can gain growth performance compared with the physical storage and virtual machines. This is necessary when storage systems work with high intensities requests.
{"title":"Development and research of models of organization storages based on the software-defined infrastructure","authors":"I. Bolodurina, D. Parfenov","doi":"10.1109/TSP.2016.7760818","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760818","url":null,"abstract":"Data centers are widely used for the placement of highly loaded applications and solutions used for the processing of large data sets (BigData). For effective access to services, minimal response time of data storages is required. We explored a new paradigm in software-defined infrastructure distributed cloud systems. Also the design principles and high-level architectural design of the SD infrastructure controller are presented here. Modern applications and services needs constantly transforming infrastructure for ensuring consumer requirements (SLAs) amidst provider constraints (costs). This paper examines infrastructure in the context of platform for new applications and services and discussing some of the fundamental characteristics required of such infrastructure called software-defined infrastructure (SDI). We developed the models of the software-defined infrastructure. We performed an experiment to analyze the productivity of software-defined storage. Our experiment has shown that software-defined storage and scheduling algorithm in software-defined infrastructure placement can gain growth performance compared with the physical storage and virtual machines. This is necessary when storage systems work with high intensities requests.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133302231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760829
A. K. Ali, I. Phillips, Huanjia Yang
Vehicular Ad-hoc Networks (VANETs) are a class of Mobile Ad-hoc Networks (MANETs) incorporated into moving vehicles. Nodes communicate with both and infrastructure to provide Intelligent Transportation Systems (ITS) for the purpose of improving safety and comfort. Efficient and adaptive routing protocols are essential for achieving reliable and scalable network performance. However, routing in VANETs is challenging due to the high-speed movement of vehicles, which results in frequent network topology changes. This paper provides an in-depth evaluation of three well-known MANET routing protocols, AODV, OLSR and GPSR, in VANET with urban environment setup. We compare their performance using three metrics: drop burst length (DBL), delay and delivery ratio (PDR). The simulations are carried out using NS2 and SUMO simulators platforms, with scenarios configured to reflect real-world conditions. The results show that OLSR is able to achieve a shorter DBL and demonstrates higher PDR performance comparing to AODV and GPSR under low network load. However, with GPSR, the network shows more stable PDR under medium and high network load. In term of delay it is outperformed by GPSR, which delivers packets with the shortest delay.
{"title":"Evaluating VANET routing in urban environments","authors":"A. K. Ali, I. Phillips, Huanjia Yang","doi":"10.1109/TSP.2016.7760829","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760829","url":null,"abstract":"Vehicular Ad-hoc Networks (VANETs) are a class of Mobile Ad-hoc Networks (MANETs) incorporated into moving vehicles. Nodes communicate with both and infrastructure to provide Intelligent Transportation Systems (ITS) for the purpose of improving safety and comfort. Efficient and adaptive routing protocols are essential for achieving reliable and scalable network performance. However, routing in VANETs is challenging due to the high-speed movement of vehicles, which results in frequent network topology changes. This paper provides an in-depth evaluation of three well-known MANET routing protocols, AODV, OLSR and GPSR, in VANET with urban environment setup. We compare their performance using three metrics: drop burst length (DBL), delay and delivery ratio (PDR). The simulations are carried out using NS2 and SUMO simulators platforms, with scenarios configured to reflect real-world conditions. The results show that OLSR is able to achieve a shorter DBL and demonstrates higher PDR performance comparing to AODV and GPSR under low network load. However, with GPSR, the network shows more stable PDR under medium and high network load. In term of delay it is outperformed by GPSR, which delivers packets with the shortest delay.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134446562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760909
Kubra Saka, O. Aydemir, Mehmet Öztürk
Brain computer interface (BCI) allows people to communicate with machines without the use of muscle systems. Although there are various kind of techniques to understand intend of the BCI user, electroencephalography (EEG) is the most popular, practical and widely implemented one. The performance of the EEG based BCI highly depends on extracting effective features. However, there is no a general feature extraction method which provides satisfied performance for all various kind of BCI applications. Therefore, it is very valuable to develop a new feature extraction method. In this paper, we proposed a novel Fast Walsh Hadamard Transform based feature extraction method for classification of EEG signals recorded during right/left hand movement imagery. It does not only provide well-discriminative attributes but also the computational time of extracting the features from a single EEG trial is fast. The proposed method was successfully applied to Data Set III of BCI competition 2003, and achieved a classification accuracy of 88.87% on the test data. The obtained satisfactory results proved that this method can be a successful alternative to the existing feature extraction methods.
{"title":"Classification of EEG signals recorded during right/left hand movement imagery using Fast Walsh Hadamard Transform based features","authors":"Kubra Saka, O. Aydemir, Mehmet Öztürk","doi":"10.1109/TSP.2016.7760909","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760909","url":null,"abstract":"Brain computer interface (BCI) allows people to communicate with machines without the use of muscle systems. Although there are various kind of techniques to understand intend of the BCI user, electroencephalography (EEG) is the most popular, practical and widely implemented one. The performance of the EEG based BCI highly depends on extracting effective features. However, there is no a general feature extraction method which provides satisfied performance for all various kind of BCI applications. Therefore, it is very valuable to develop a new feature extraction method. In this paper, we proposed a novel Fast Walsh Hadamard Transform based feature extraction method for classification of EEG signals recorded during right/left hand movement imagery. It does not only provide well-discriminative attributes but also the computational time of extracting the features from a single EEG trial is fast. The proposed method was successfully applied to Data Set III of BCI competition 2003, and achieved a classification accuracy of 88.87% on the test data. The obtained satisfactory results proved that this method can be a successful alternative to the existing feature extraction methods.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"22 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120905601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760972
R. Szabó, A. Gontean, A. Sfirat
In this paper a robotic arm control, with color recognition, implemented on a Raspberry PI, will be presented. The Raspberry PI is a small super computer which is suitable for almost any embedded project. To the Raspberry PI is connected a Logitech C270 web camera or a TP-LINK TL-SC3230 IP camera and a USB to serial dongle which does the communication task. The camera pair films the robotic arm and the USB to serial dongle controls the robotic arm. The color recognition is done with OpenCV installed on the Raspberry PI. The robotic arm has glued colored bottle stoppers on the joints which are recognized with color filtering. These joints are united with lines and other lines are drawn to be guide lines to some mathematical computations. Based on these lines a skeleton of the robotic arm is created, which is an info for the Raspberry PI about the position in space of the robotic arm. With further computations the robotic arm can be moved in the desired position.
{"title":"Robotic arm control in space with color recognition using a Raspberry PI","authors":"R. Szabó, A. Gontean, A. Sfirat","doi":"10.1109/TSP.2016.7760972","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760972","url":null,"abstract":"In this paper a robotic arm control, with color recognition, implemented on a Raspberry PI, will be presented. The Raspberry PI is a small super computer which is suitable for almost any embedded project. To the Raspberry PI is connected a Logitech C270 web camera or a TP-LINK TL-SC3230 IP camera and a USB to serial dongle which does the communication task. The camera pair films the robotic arm and the USB to serial dongle controls the robotic arm. The color recognition is done with OpenCV installed on the Raspberry PI. The robotic arm has glued colored bottle stoppers on the joints which are recognized with color filtering. These joints are united with lines and other lines are drawn to be guide lines to some mathematical computations. Based on these lines a skeleton of the robotic arm is created, which is an info for the Raspberry PI about the position in space of the robotic arm. With further computations the robotic arm can be moved in the desired position.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124934580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-27DOI: 10.1109/TSP.2016.7760903
Ş. Aymaz, Tugrul Çavdar
This paper presents a developed device to solve the problem of moving and navigating of visually impaired and blind people. This device, called Ultrasonic Assistive Headset, is light, simple and low-cost option compared with other assistive devices. Ultrasonic Assistive Headset will guide for them among obstacles by employing ultrasonic distance sensors, microcontroller, voice storage circuit and solar panels to be battery-free. In proposed method, ultrasonic waves arrive to the ultrasonic sensors on the spherical membrane of the headset after sending this waves from ultrasonic distance sensors reflection from obstacles. A microcontroller determines the location of the obstacles according to the sensor ID and the information of distance. The system produces an voice data defining the location, and then it speaks to blind person where the obstacles are. Ultrasonic Assistive Headset can be used easily by them both indoor and outdoor, so they can avoid obstacles quickly and accurately.
{"title":"Ultrasonic Assistive Headset for visually impaired people","authors":"Ş. Aymaz, Tugrul Çavdar","doi":"10.1109/TSP.2016.7760903","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760903","url":null,"abstract":"This paper presents a developed device to solve the problem of moving and navigating of visually impaired and blind people. This device, called Ultrasonic Assistive Headset, is light, simple and low-cost option compared with other assistive devices. Ultrasonic Assistive Headset will guide for them among obstacles by employing ultrasonic distance sensors, microcontroller, voice storage circuit and solar panels to be battery-free. In proposed method, ultrasonic waves arrive to the ultrasonic sensors on the spherical membrane of the headset after sending this waves from ultrasonic distance sensors reflection from obstacles. A microcontroller determines the location of the obstacles according to the sensor ID and the information of distance. The system produces an voice data defining the location, and then it speaks to blind person where the obstacles are. Ultrasonic Assistive Headset can be used easily by them both indoor and outdoor, so they can avoid obstacles quickly and accurately.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"378 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128090666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-01DOI: 10.1109/TSP.2016.7760899
O. Aydemir
Electroencephalogram (EEG), which is widely used for brain computer interface (BCI) systems for input signal, is easily interrupted by physical or mental tasks, and contaminated with various artifacts including power line noise, electromyogram and electrocardiogram. Therefore, such kind of artifacts cause to decrease the accuracy rate and motivate the researchers substantially develop the performance of all components of the communication system between the subject and a BCI output device. So, it is vital to use the most suitable classification algorithm and fewer feature set to implement a fast and accurate BCI system. Addition to this, it is worthwhile mentioning that the classifiers should have the ability for recognizing signals which are collected in different sessions to make brain computer interfaces practical in use. In this study, we proposed fast and accurate classification method for classifying EEG data of up/down/right/left computer cursor movement imagery. EEG signals were collected from three healthy male adults and on two different offline sessions with about one week of delay. The average test classification accuracy calculated as 53.07%.
{"title":"Classification of 2-dimensional cursor movement imagery EEG signals","authors":"O. Aydemir","doi":"10.1109/TSP.2016.7760899","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760899","url":null,"abstract":"Electroencephalogram (EEG), which is widely used for brain computer interface (BCI) systems for input signal, is easily interrupted by physical or mental tasks, and contaminated with various artifacts including power line noise, electromyogram and electrocardiogram. Therefore, such kind of artifacts cause to decrease the accuracy rate and motivate the researchers substantially develop the performance of all components of the communication system between the subject and a BCI output device. So, it is vital to use the most suitable classification algorithm and fewer feature set to implement a fast and accurate BCI system. Addition to this, it is worthwhile mentioning that the classifiers should have the ability for recognizing signals which are collected in different sessions to make brain computer interfaces practical in use. In this study, we proposed fast and accurate classification method for classifying EEG data of up/down/right/left computer cursor movement imagery. EEG signals were collected from three healthy male adults and on two different offline sessions with about one week of delay. The average test classification accuracy calculated as 53.07%.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124874770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-01DOI: 10.1109/TSP.2016.7760823
Dennis Modig, Jianguo Ding
Over the past years the use of digital devices has increased and home networks continue to grow in size and complexity. By the use of virtualized residential gateways advanced functionality can be moved away from the home by extending the customers edge network to the Internet Service Provider (ISP) and thereby decrease the administrative burden for the home user. By employing edge computing and cloud applications at the operator by virtualizing residential gateways instead of using physical devices creates new challenges. This paper is looking at how the choice of virtualization technology impacts performance by investigating operating system level virtualization in contrast to full virtualization for use in virtualized residential gateways. Results show that container based virtualization uses fewer resources in terms of disk, memory, and processor in virtualized residential gateways.
{"title":"Performance impacts on container based virtualization in virtualized residential gateways","authors":"Dennis Modig, Jianguo Ding","doi":"10.1109/TSP.2016.7760823","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760823","url":null,"abstract":"Over the past years the use of digital devices has increased and home networks continue to grow in size and complexity. By the use of virtualized residential gateways advanced functionality can be moved away from the home by extending the customers edge network to the Internet Service Provider (ISP) and thereby decrease the administrative burden for the home user. By employing edge computing and cloud applications at the operator by virtualizing residential gateways instead of using physical devices creates new challenges. This paper is looking at how the choice of virtualization technology impacts performance by investigating operating system level virtualization in contrast to full virtualization for use in virtualized residential gateways. Results show that container based virtualization uses fewer resources in terms of disk, memory, and processor in virtualized residential gateways.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125151933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-01DOI: 10.1109/TSP.2016.7760933
Garima Vyas, M. Dutta, J. Prinosil, P. Harár
To diagnose and classify the dysarthric speech, speech language pathologist (SLP) conducts a listening test. On the basis of the scores given by listeners the dysarthria is diagnosed and assessed. The above mentioned method is costly, time consuming and not very accurate. Unlike the traditional method, this research proposes an automatic diagnosis and assessment of dysarthria. The aim of this paper is to diagnose and classify the severity of dysarthria. The speech disorder specific prosodic features are selected by using genetic algorithm. The diagnosis and assessment of dysarthric speech is done by support vector machines. During diagnosis the classification accuracy of 98% has been achieved. And 87% of the dysarthric speech utterances are correctly classified. The standard UASPEECH database has been used in this work.
{"title":"An automatic diagnosis and assessment of dysarthric speech using speech disorder specific prosodic features","authors":"Garima Vyas, M. Dutta, J. Prinosil, P. Harár","doi":"10.1109/TSP.2016.7760933","DOIUrl":"https://doi.org/10.1109/TSP.2016.7760933","url":null,"abstract":"To diagnose and classify the dysarthric speech, speech language pathologist (SLP) conducts a listening test. On the basis of the scores given by listeners the dysarthria is diagnosed and assessed. The above mentioned method is costly, time consuming and not very accurate. Unlike the traditional method, this research proposes an automatic diagnosis and assessment of dysarthria. The aim of this paper is to diagnose and classify the severity of dysarthria. The speech disorder specific prosodic features are selected by using genetic algorithm. The diagnosis and assessment of dysarthric speech is done by support vector machines. During diagnosis the classification accuracy of 98% has been achieved. And 87% of the dysarthric speech utterances are correctly classified. The standard UASPEECH database has been used in this work.","PeriodicalId":159773,"journal":{"name":"2016 39th International Conference on Telecommunications and Signal Processing (TSP)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116752803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：