Pub Date : 2014-11-03DOI: 10.1109/CCNC.2014.6940487
Pierre Meye, Philippe Raipin, F. Tronel, E. Anceaume
Internet Service Providers (ISP) furnishing cloud storage services usually rely on big data centers. These centralized architectures induce many drawbacks in terms of scalability and reliability as datacenters represent single points of failure, and in terms of data access latencies as they are not necessarily located close to the users. This paper presents the design choices about a distributed storage system that targets these issues by leveraging only high available nodes in the Digital Subscriber Line (xDSL) infrastructure of an ISP, namely a large number of home gateways, Points of Presence, and datacenters.
{"title":"Toward a distributed storage system leveraging the DSL infrastructure of an ISP","authors":"Pierre Meye, Philippe Raipin, F. Tronel, E. Anceaume","doi":"10.1109/CCNC.2014.6940487","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940487","url":null,"abstract":"Internet Service Providers (ISP) furnishing cloud storage services usually rely on big data centers. These centralized architectures induce many drawbacks in terms of scalability and reliability as datacenters represent single points of failure, and in terms of data access latencies as they are not necessarily located close to the users. This paper presents the design choices about a distributed storage system that targets these issues by leveraging only high available nodes in the Digital Subscriber Line (xDSL) infrastructure of an ISP, namely a large number of home gateways, Points of Presence, and datacenters.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116766990","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940529
A. Jara, Yann Bocchi, D. Genoud
The potential of the artificial intelligence to build solutions based on the understanding of human behaviours, and the capacity to discover patterns through their interactions with the world is being extended with the capabilities of the Internet of Things. The described potential, so-called Human Dynamics, pursues to describe in real-time the human behaviours and activities. These goals are starting to be feasible through the quantity of data provided by two of the main areas of the Internet of Things, on the one hand, the Smart cities to make more intelligent the environment and offer a smart space that sense our movements, actions, and the evolution of the ecosystem, and on the other hand, the wearable and mobile computing which allows to provide data from the humans itself, i.e., from their pockets (smart phones), wrists (smart watches), hearts (wearable sensors), and eyes (glasses). This work analyses the ecosystem defined through the triangle formed by Big Data, Smart Cities and Wearable Computing to determinate human dynamics. For this purpose, the life-cycle of human dynamics determinations in Smart Cities have been analysed in order to determinate the current status of the technology, challenges, and opportunities.
{"title":"Mobility management in bluetooth low energy","authors":"A. Jara, Yann Bocchi, D. Genoud","doi":"10.1109/CCNC.2014.6940529","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940529","url":null,"abstract":"The potential of the artificial intelligence to build solutions based on the understanding of human behaviours, and the capacity to discover patterns through their interactions with the world is being extended with the capabilities of the Internet of Things. The described potential, so-called Human Dynamics, pursues to describe in real-time the human behaviours and activities. These goals are starting to be feasible through the quantity of data provided by two of the main areas of the Internet of Things, on the one hand, the Smart cities to make more intelligent the environment and offer a smart space that sense our movements, actions, and the evolution of the ecosystem, and on the other hand, the wearable and mobile computing which allows to provide data from the humans itself, i.e., from their pockets (smart phones), wrists (smart watches), hearts (wearable sensors), and eyes (glasses). This work analyses the ecosystem defined through the triangle formed by Big Data, Smart Cities and Wearable Computing to determinate human dynamics. For this purpose, the life-cycle of human dynamics determinations in Smart Cities have been analysed in order to determinate the current status of the technology, challenges, and opportunities.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129726802","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940517
Ruobin Zheng, Wenle Yang, Jun Zhou
In the cloud era, booming broadband access, and the new services that it facilitates, is posing a greater demand on access technologies. Legacy access technologies are facing lots of challenges: Complexity for multi-point access management; Scalability and energy efficiency in remote nodes; Painfulness of choosing a technology; Difficulty of access network wholesale. To address these challenges, this paper discusses Software-defined Access Networks (SDAN) as the next-gen architecture for access networking. With its simplified access nodes, flexible and programmable line technologies, and cloud home gateway & services, SDAN helps operators construct a simple, agile, elastic, and value-added access network.
{"title":"Future access architecture: Software-defined accesss networking","authors":"Ruobin Zheng, Wenle Yang, Jun Zhou","doi":"10.1109/CCNC.2014.6940517","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940517","url":null,"abstract":"In the cloud era, booming broadband access, and the new services that it facilitates, is posing a greater demand on access technologies. Legacy access technologies are facing lots of challenges: Complexity for multi-point access management; Scalability and energy efficiency in remote nodes; Painfulness of choosing a technology; Difficulty of access network wholesale. To address these challenges, this paper discusses Software-defined Access Networks (SDAN) as the next-gen architecture for access networking. With its simplified access nodes, flexible and programmable line technologies, and cloud home gateway & services, SDAN helps operators construct a simple, agile, elastic, and value-added access network.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121451752","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940488
M. Rahmes, Rick Pemble, G. Lemieux, K. Fox
We describe a model for determining strategies for making decisions for sensor prioritization strategies. We combine operations research methods and remote sensing for decision making with several possible actions, state of the world, and a mixed probability metric. We perform data mining and discover patterns to automatically enhance situational awareness from multiple sensor inputs. Our solution has been developed for a method for determining actionable information to efficiently manage remote sensing assets and use open source information. Our tool allows for calculating optimal strategies, provides greater knowledge about the state of the world, and increases the likelihood of a decision maker making the best decision. We discuss multi-dimensional game theory using linear programming methods to solve for multiple possible strategies. We discuss a new concept of reward volumes. The decision maker's success depends upon his ability to correctly and automatically judge the multiple factors. The goal of our system, called GlobalSite, is to deliver trustworthy threat analysis systems and services that understand situations, while being a vital tool for continuing mission operations.
{"title":"Multi-dimensional reward volumes for sensor priority strategies","authors":"M. Rahmes, Rick Pemble, G. Lemieux, K. Fox","doi":"10.1109/CCNC.2014.6940488","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940488","url":null,"abstract":"We describe a model for determining strategies for making decisions for sensor prioritization strategies. We combine operations research methods and remote sensing for decision making with several possible actions, state of the world, and a mixed probability metric. We perform data mining and discover patterns to automatically enhance situational awareness from multiple sensor inputs. Our solution has been developed for a method for determining actionable information to efficiently manage remote sensing assets and use open source information. Our tool allows for calculating optimal strategies, provides greater knowledge about the state of the world, and increases the likelihood of a decision maker making the best decision. We discuss multi-dimensional game theory using linear programming methods to solve for multiple possible strategies. We discuss a new concept of reward volumes. The decision maker's success depends upon his ability to correctly and automatically judge the multiple factors. The goal of our system, called GlobalSite, is to deliver trustworthy threat analysis systems and services that understand situations, while being a vital tool for continuing mission operations.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114259952","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940524
M. Roccetti, G. Marfia, S. Colombini, M. Zanichelli
Museums and exhibitions traditionally present pieces of preserved human knowledge in a static manner, letting their public observe and analyze what can be heard or seen. Sight and hearing are hence the two senses, out of the five available ones, that are usually engaged in such scenarios. Recently, information and communication technologies have been put to good use to increase the amount of participation that visitors experience while seeing an exhibition, engaging for example the other senses (taste, smell and touch) in playful ways with modern sensors and actuators, but also serving as building blocks for applications that support novel methodologies of knowledge transfer. In fact, the ephemeral part of human knowledge and experience is the most difficult to capture and, consequently, the hardest to hand down to posterity. Although this remains an open challenge, far from being definitely solved, many steps forward have been made so far. It is hence today possible to go beyond watching or listening, supporting the performance of actions and the construction of new practical experiences while visiting a museum or an exhibition. In this paper we describe practical example of how we implemented such ideas in an interactive system that will be shown in downtown Rome at the Trajan Forum Exposition center. In brief, we constructed an interactive system that lets visitors playing a piano together with the Italian Jazz star Lelio Luttazzi. Visitors, hence, can participate and build their own experience playing with the real artist, rather than solely listening to the artist's music or watching the artist's pictures.
{"title":"LelioSwing: Rediscovering music classics while playing in duo with Lelio Luttazzi","authors":"M. Roccetti, G. Marfia, S. Colombini, M. Zanichelli","doi":"10.1109/CCNC.2014.6940524","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940524","url":null,"abstract":"Museums and exhibitions traditionally present pieces of preserved human knowledge in a static manner, letting their public observe and analyze what can be heard or seen. Sight and hearing are hence the two senses, out of the five available ones, that are usually engaged in such scenarios. Recently, information and communication technologies have been put to good use to increase the amount of participation that visitors experience while seeing an exhibition, engaging for example the other senses (taste, smell and touch) in playful ways with modern sensors and actuators, but also serving as building blocks for applications that support novel methodologies of knowledge transfer. In fact, the ephemeral part of human knowledge and experience is the most difficult to capture and, consequently, the hardest to hand down to posterity. Although this remains an open challenge, far from being definitely solved, many steps forward have been made so far. It is hence today possible to go beyond watching or listening, supporting the performance of actions and the construction of new practical experiences while visiting a museum or an exhibition. In this paper we describe practical example of how we implemented such ideas in an interactive system that will be shown in downtown Rome at the Trajan Forum Exposition center. In brief, we constructed an interactive system that lets visitors playing a piano together with the Italian Jazz star Lelio Luttazzi. Visitors, hence, can participate and build their own experience playing with the real artist, rather than solely listening to the artist's music or watching the artist's pictures.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114771931","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940500
Junghyo Lee, P. Seeling
In this paper, we present a mobile-device level approach to estimating the network data (traffic) that is generated over time. While efforts oftentimes utilize complex approaches, our model captures the main characteristics in the time and data domains of a high utilization application class as Hidden Markov Model while modeling the remaining applications' characteristics in form of a simple background process. We find that our approach is capable of matching the average amounts of data behavior of the source dataset (with a reduction in overall variability of the simulated produced traffic as drawback) and is thus suitable for high level capacity evaluations.
{"title":"Mobile device-level data modeling through high utilization mobile applications","authors":"Junghyo Lee, P. Seeling","doi":"10.1109/CCNC.2014.6940500","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940500","url":null,"abstract":"In this paper, we present a mobile-device level approach to estimating the network data (traffic) that is generated over time. While efforts oftentimes utilize complex approaches, our model captures the main characteristics in the time and data domains of a high utilization application class as Hidden Markov Model while modeling the remaining applications' characteristics in form of a simple background process. We find that our approach is capable of matching the average amounts of data behavior of the source dataset (with a reduction in overall variability of the simulated produced traffic as drawback) and is thus suitable for high level capacity evaluations.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115291350","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940515
Troy A. Johnson, P. Seeling
As mobile data consumption increases, several venues of research investigate energy efficiency and optimizations, oftentimes realized through on-device services; optimization approaches based around on-device optimizations in turn need to overcome the power consumption added by these services. We present a measurement framework for the power consumption of mobile devices based on the Pandaboard (mobile) development platform using the Android operating system. Utilizing the framework, we perform power consumption evaluations for basic web requests as well as HTML5 video streaming to a mobile browser in (i) direct connection and (ii) indirect connections through a mobile proxy server on the device, which represents a baseline for application layer optimization approaches. We find that using the local proxy server on the device for web requests results in very limited overheads, both in terms of power consumption and added delays which tend to remain request size independent. HTML5 video streaming through the proxy service incurs an average energy consumption penalty of approximately one percent. Our findings corroborate that even smaller realized optimization gains through services on mobile devices themselves are not usurped by the service enablers consuming mobile CPU cycles.
{"title":"Power consumption overhead for proxy services on mobile device platforms","authors":"Troy A. Johnson, P. Seeling","doi":"10.1109/CCNC.2014.6940515","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940515","url":null,"abstract":"As mobile data consumption increases, several venues of research investigate energy efficiency and optimizations, oftentimes realized through on-device services; optimization approaches based around on-device optimizations in turn need to overcome the power consumption added by these services. We present a measurement framework for the power consumption of mobile devices based on the Pandaboard (mobile) development platform using the Android operating system. Utilizing the framework, we perform power consumption evaluations for basic web requests as well as HTML5 video streaming to a mobile browser in (i) direct connection and (ii) indirect connections through a mobile proxy server on the device, which represents a baseline for application layer optimization approaches. We find that using the local proxy server on the device for web requests results in very limited overheads, both in terms of power consumption and added delays which tend to remain request size independent. HTML5 video streaming through the proxy service incurs an average energy consumption penalty of approximately one percent. Our findings corroborate that even smaller realized optimization gains through services on mobile devices themselves are not usurped by the service enablers consuming mobile CPU cycles.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116487592","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940523
Benjamin Rainer, C. Timmerer, Patrick Kapahnke, M. Klusch
With the introduction of social networks like Facebook, Google+, and Twitter, the ways of sharing impressions of events has changed. We try to go a step further than social networks do. We offer the possibility to share events live with friends and colleagues. Our approach is based on semantic search in unstructured peer-to-peer (P2P) networks for querying content in mobile ad hoc networks and dynamic adaptive streaming over HTTP for the actual delivery of the real-time media impressions.
{"title":"Real-time multimedia streaming in unstructured peer-to-peer networks","authors":"Benjamin Rainer, C. Timmerer, Patrick Kapahnke, M. Klusch","doi":"10.1109/CCNC.2014.6940523","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940523","url":null,"abstract":"With the introduction of social networks like Facebook, Google+, and Twitter, the ways of sharing impressions of events has changed. We try to go a step further than social networks do. We offer the possibility to share events live with friends and colleagues. Our approach is based on semantic search in unstructured peer-to-peer (P2P) networks for querying content in mobile ad hoc networks and dynamic adaptive streaming over HTTP for the actual delivery of the real-time media impressions.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115140572","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940486
M. Roccetti, Cristian Bertuccioli, A. Marcomini, Angelo Varni, G. Marfia, M. Zanichelli
As mobile devices have pervasively become virtually available to all, cultural institutions have been increasingly investing resources in the creation of apps that can be enjoyed on the phone. Typically such apps are built custom for specific events or exhibitions, resulting in increased IT costs that well exceed the typical costs due to the maintenance of institutional websites and the carry on of traditional marketing strategies. In this paper we describe Museo Multiverso (MuMu), a mobile publishing platform that provides a standard interface with the mobile world to museum curators and experts. Using MuMu a museum curator can populate a mobile client with any multimedia information related to an exhibition or to a network of exhibitions and easily publish such information and make it available to mobile users. MuMu is composed of two main components: a platform that museum curators can use to organize and insert the information they want to share with the public and a mobile client where users can originally enjoy all of such information. In fact, the contribution of this work is twofold: (a) from an architectural point of view, we designed and implemented a platform that can be put to good use to support virtually any number of museums and events, and, (b) from a human-computer interaction point of view we leverage on advanced interaction techniques in order to provide an easy to use interface that excites curiosity and interest.
{"title":"Museo Multiverso: Bridging the gap between museums and mobile platforms","authors":"M. Roccetti, Cristian Bertuccioli, A. Marcomini, Angelo Varni, G. Marfia, M. Zanichelli","doi":"10.1109/CCNC.2014.6940486","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940486","url":null,"abstract":"As mobile devices have pervasively become virtually available to all, cultural institutions have been increasingly investing resources in the creation of apps that can be enjoyed on the phone. Typically such apps are built custom for specific events or exhibitions, resulting in increased IT costs that well exceed the typical costs due to the maintenance of institutional websites and the carry on of traditional marketing strategies. In this paper we describe Museo Multiverso (MuMu), a mobile publishing platform that provides a standard interface with the mobile world to museum curators and experts. Using MuMu a museum curator can populate a mobile client with any multimedia information related to an exhibition or to a network of exhibitions and easily publish such information and make it available to mobile users. MuMu is composed of two main components: a platform that museum curators can use to organize and insert the information they want to share with the public and a mobile client where users can originally enjoy all of such information. In fact, the contribution of this work is twofold: (a) from an architectural point of view, we designed and implemented a platform that can be put to good use to support virtually any number of museums and events, and, (b) from a human-computer interaction point of view we leverage on advanced interaction techniques in order to provide an easy to use interface that excites curiosity and interest.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126625027","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 : 2014-11-03DOI: 10.1109/CCNC.2014.6940492
A. Jagatheesan, Jong-Roon Ahnn, T. Phan, Abhishek Singh, Juhan Lee
Automatic Speech Recognition (ASR) has evolved remarkably over the years and is expected to become a primary form of input to mobile devices including smartphones and wearables. Most large-scale mobile platforms perform speech recognition in the cloud today. There are both advantages and disadvantages to this Cloud-based ASR (Cloud-ASR) approach. Cloud-ASR approach allows for a context oriented humancomputer- interaction using speech rather than a mere speech-totext translation. A Cloud-ASR also has disadvantages such as interruption of the speech service when there is no access to the Cloud-ASR, and also the energy consumption for radio communications, which can drain a mobile battery sooner. We propose the usage of Hierarchical Speech Recognizer (HSR) as an alternative approach to overcome the shortcomings of the Cloud-ASR approach. In the HSR approach, mobile devices perform "selective speech recognition" by themselves as much as possible without contacting an external cloud-based ASR service. In this demonstration, we show our proof-of-concept HSR along with its feasibility and advantages.
{"title":"Hierarchical automatic speech recognition powered by data infrastructure","authors":"A. Jagatheesan, Jong-Roon Ahnn, T. Phan, Abhishek Singh, Juhan Lee","doi":"10.1109/CCNC.2014.6940492","DOIUrl":"https://doi.org/10.1109/CCNC.2014.6940492","url":null,"abstract":"Automatic Speech Recognition (ASR) has evolved remarkably over the years and is expected to become a primary form of input to mobile devices including smartphones and wearables. Most large-scale mobile platforms perform speech recognition in the cloud today. There are both advantages and disadvantages to this Cloud-based ASR (Cloud-ASR) approach. Cloud-ASR approach allows for a context oriented humancomputer- interaction using speech rather than a mere speech-totext translation. A Cloud-ASR also has disadvantages such as interruption of the speech service when there is no access to the Cloud-ASR, and also the energy consumption for radio communications, which can drain a mobile battery sooner. We propose the usage of Hierarchical Speech Recognizer (HSR) as an alternative approach to overcome the shortcomings of the Cloud-ASR approach. In the HSR approach, mobile devices perform \"selective speech recognition\" by themselves as much as possible without contacting an external cloud-based ASR service. In this demonstration, we show our proof-of-concept HSR along with its feasibility and advantages.","PeriodicalId":287724,"journal":{"name":"2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123530307","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：