Pub Date : 2004-09-13DOI: 10.1109/WDM.2004.1358101
C. Serrão, Gregor Siegert
This work would start by describing OpenSDRM an open-source framework developed for the IST project MOSES., OpenSDRM is used to control the multimedia content consumption in conjunction with the new IPMPX MPEG-4 proposed standard. This architecture, composed by several building blocks, protects the content flow from creation to final user consumption on a specific device. This work devotes a special attention to the security aspects of the OpenSDRM processes and functions, describing its communication protocols and message exchanges as well as it introduces the security details about the user's digital wallet.
{"title":"Open secure infrastructure to control user access to multimedia content","authors":"C. Serrão, Gregor Siegert","doi":"10.1109/WDM.2004.1358101","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358101","url":null,"abstract":"This work would start by describing OpenSDRM an open-source framework developed for the IST project MOSES., OpenSDRM is used to control the multimedia content consumption in conjunction with the new IPMPX MPEG-4 proposed standard. This architecture, composed by several building blocks, protects the content flow from creation to final user consumption on a specific device. This work devotes a special attention to the security aspects of the OpenSDRM processes and functions, describing its communication protocols and message exchanges as well as it introduces the security details about the user's digital wallet.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123841153","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358105
N. Oikonomidis, C. Ruland
Contemporary systems for distribution of electronic media content and its respective licenses are limited in a way that neither the consumers nor the vendors can operate in a reliable and flexible way. Further, the security architecture that comprises these systems is based and literally mapped upon them from security architectures, which apply to distributed systems based on computer terminals and not necessarily on mobile devices. The attempt to apply such architectures on the world of mobile multimedia so far has lead to solutions, which mostly rely on one single certification authority. It is more than obvious that this fact introduces the fatal risk of having a single-point-of-attack, since a compromise of the CA's private key leads to a compromise of the entire system. Our proposal introduces protocols that utilize ID-based cryptographic methods, in order to provide electronic content delivery and licensing.
{"title":"Identity based protocols for secure electronic content distribution and licensing","authors":"N. Oikonomidis, C. Ruland","doi":"10.1109/WDM.2004.1358105","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358105","url":null,"abstract":"Contemporary systems for distribution of electronic media content and its respective licenses are limited in a way that neither the consumers nor the vendors can operate in a reliable and flexible way. Further, the security architecture that comprises these systems is based and literally mapped upon them from security architectures, which apply to distributed systems based on computer terminals and not necessarily on mobile devices. The attempt to apply such architectures on the world of mobile multimedia so far has lead to solutions, which mostly rely on one single certification authority. It is more than obvious that this fact introduces the fatal risk of having a single-point-of-attack, since a compromise of the CA's private key leads to a compromise of the entire system. Our proposal introduces protocols that utilize ID-based cryptographic methods, in order to provide electronic content delivery and licensing.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124329996","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358106
D. Politis, D. Margounakis, Konstantinos Mokos
Musical imaging is a recent trend in visualizing "hidden" dimensions of one-dimensional audio signals. The ascription of colors to psychoacoustic phenomena is consistent to the music perception depicted in the variety of scales and styles of ethnic music. Audio tools based on software engineering techniques are built for visualizing the chrominance of global music. This work presents MEL-IRIS, an audio tool that supports the chromatic indexing of music. Chromatic description can be used for classification, identification, making queries based on emotion and characterization of the style of an artist. Chromatic metadata can comprise a novel way in music retrieval in Web-based applications.
{"title":"Visualizing the chromatic index of music","authors":"D. Politis, D. Margounakis, Konstantinos Mokos","doi":"10.1109/WDM.2004.1358106","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358106","url":null,"abstract":"Musical imaging is a recent trend in visualizing \"hidden\" dimensions of one-dimensional audio signals. The ascription of colors to psychoacoustic phenomena is consistent to the music perception depicted in the variety of scales and styles of ethnic music. Audio tools based on software engineering techniques are built for visualizing the chrominance of global music. This work presents MEL-IRIS, an audio tool that supports the chromatic indexing of music. Chromatic description can be used for classification, identification, making queries based on emotion and characterization of the style of an artist. Chromatic metadata can comprise a novel way in music retrieval in Web-based applications.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132692790","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358108
F. Seifert
Besides audio fingerprinting techniques there are no essential procedures for a content-based identification of music audio available. But even these techniques rely heavily on statistical information of audio and do not consider any semantics of music. Furthermore, they require each piece of music to be pre-recorded and thus pre-processed for a successful identification. We try to apply the leadsheet-model - a generic model for processing tonal music - on content-based audio identification and show how it can be altered to handle audio. As a result we are capable of identifying music with extremely varying spectra based on only one given template.
{"title":"Semantic music recognition - audio identification beyond fingerprinting","authors":"F. Seifert","doi":"10.1109/WDM.2004.1358108","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358108","url":null,"abstract":"Besides audio fingerprinting techniques there are no essential procedures for a content-based identification of music audio available. But even these techniques rely heavily on statistical information of audio and do not consider any semantics of music. Furthermore, they require each piece of music to be pre-recorded and thus pre-processed for a successful identification. We try to apply the leadsheet-model - a generic model for processing tonal music - on content-based audio identification and show how it can be altered to handle audio. As a result we are capable of identifying music with extremely varying spectra based on only one given template.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129851944","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358098
P. Bellini, J. Barthélemy, P. Nesi, G. Zoia
Integration of music notation in multimedia frameworks, and particularly in MPEG, could open new ways of valorization for that important part of our cultural heritage that is known as "music notation". Integration of music notation with multimedia content could also increase the distribution and diffusion of music notation. Moreover, integration with video, interactivity, digital rights management would enable the development of a huge number of completely new applications in several domains, from education and distance learning, to rehearsal and musical practice at home, and any forms of enjoyment of music that can be imagined. For these reasons we started a work for integrating symbolic music representation into MPEG standardization process and format. A proposal for realizing this integration in the MPEG-4 players is presented together with the main relationships that the symbolic music representation could have with all the MPEG components. The proposal is grounded on the basis of the assessment of the requirements of a large set of emerging new applications in which music notation is synchronized with multimedia content.
{"title":"A proposal for the integration of symbolic music notation into multimedia frameworks","authors":"P. Bellini, J. Barthélemy, P. Nesi, G. Zoia","doi":"10.1109/WDM.2004.1358098","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358098","url":null,"abstract":"Integration of music notation in multimedia frameworks, and particularly in MPEG, could open new ways of valorization for that important part of our cultural heritage that is known as \"music notation\". Integration of music notation with multimedia content could also increase the distribution and diffusion of music notation. Moreover, integration with video, interactivity, digital rights management would enable the development of a huge number of completely new applications in several domains, from education and distance learning, to rehearsal and musical practice at home, and any forms of enjoyment of music that can be imagined. For these reasons we started a work for integrating symbolic music representation into MPEG standardization process and format. A proposal for realizing this integration in the MPEG-4 players is presented together with the main relationships that the symbolic music representation could have with all the MPEG components. The proposal is grounded on the basis of the assessment of the requirements of a large set of emerging new applications in which music notation is synchronized with multimedia content.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"17 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113981147","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358094
L. O. Endelt, A. L. Cour-Harbo
When using a discrete wavelet transform or a wavelet packet for obtaining a sparse representation of music-signals the first question that arises is which wavelet filter/mother wavelet to use. The sparseness is a measure of how fast the DWT coefficients decay, and we are interested in obtaining a representation where the energy of the signal is concentrated in a few of the DWT coefficients. It is well-known that the decay of the DWT coefficients is strongly related to the number of vanishing moments of the mother wavelet, and to the smoothness of the signal. We present the result of applying two classical families of wavelets to a series of musical signals. The purpose is to determine a general relation between the number of vanishing moments of the wavelet and the sparseness of the DWT coefficients, when applied to music signals.
{"title":"Wavelets for sparse representation of music","authors":"L. O. Endelt, A. L. Cour-Harbo","doi":"10.1109/WDM.2004.1358094","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358094","url":null,"abstract":"When using a discrete wavelet transform or a wavelet packet for obtaining a sparse representation of music-signals the first question that arises is which wavelet filter/mother wavelet to use. The sparseness is a measure of how fast the DWT coefficients decay, and we are interested in obtaining a representation where the energy of the signal is concentrated in a few of the DWT coefficients. It is well-known that the decay of the DWT coefficients is strongly related to the number of vanishing moments of the mother wavelet, and to the smoothness of the signal. We present the result of applying two classical families of wavelets to a series of musical signals. The purpose is to determine a general relation between the number of vanishing moments of the wavelet and the sparseness of the DWT coefficients, when applied to music signals.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121133105","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358096
Marcos Alonso, G. Geiger, S. Jordà
We present an Internet browser plug-in for interactive real-time sound synthesis. The plug-in runs the pure data (Pd) sound synthesis engine within the browser, and allows flexible and transparent sound generation and control. Pd is a general sound synthesis language that is based on the MAX graphical programming paradigm, which allows constructing and implementing a broad range of sound synthesis algorithms and paradigms, ranging from simple MIDI-like sample playback up to interactive sound generation and manipulation. This plug-in is cross-platform and runs on Windows Internet Explorer as well as on Netscape/Mozilla on Windows, OSX and Linux platforms. It opens a wide range of new possibilities for the presentation of dynamic multimedia content, where sound plays an important role and the playback of static sound files is not anymore sufficient. The data used by the plug-in that has to be transmitted over the net, is very small in size and thus perfectly suitable for low bandwidth connections. Examples of potential applications are games, adaptive sound backgrounds, interactive sound installations, Web sites, collaborative music on the Web, education and e-learning. The first implementation of the Pd plug-in has been written for a project collaboration with the Catalan theater group "La Fura dels Baus".
我们提出了一个用于交互式实时声音合成的Internet浏览器插件。该插件在浏览器内运行纯数据(Pd)声音合成引擎，并允许灵活透明的声音生成和控制。Pd是一种基于MAX图形编程范式的通用声音合成语言，它允许构建和实现广泛的声音合成算法和范式，范围从简单的midi样例回放到交互式声音生成和操作。此插件是跨平台的，可在Windows Internet Explorer以及Windows、OSX和Linux平台上的Netscape/Mozilla上运行。它为动态多媒体内容的呈现提供了广泛的新可能性，其中声音起着重要作用，而静态声音文件的播放不再足够。必须通过网络传输的插件所使用的数据非常小，因此非常适合低带宽连接。潜在应用的例子包括游戏、自适应声音背景、交互式声音安装、Web站点、Web上的协作音乐、教育和电子学习。Pd插件的第一个实现是为一个与加泰罗尼亚戏剧团体“La Fura dels Baus”合作的项目编写的。
{"title":"An Internet browser plug-in for real-time audio synthesis","authors":"Marcos Alonso, G. Geiger, S. Jordà","doi":"10.1109/WDM.2004.1358096","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358096","url":null,"abstract":"We present an Internet browser plug-in for interactive real-time sound synthesis. The plug-in runs the pure data (Pd) sound synthesis engine within the browser, and allows flexible and transparent sound generation and control. Pd is a general sound synthesis language that is based on the MAX graphical programming paradigm, which allows constructing and implementing a broad range of sound synthesis algorithms and paradigms, ranging from simple MIDI-like sample playback up to interactive sound generation and manipulation. This plug-in is cross-platform and runs on Windows Internet Explorer as well as on Netscape/Mozilla on Windows, OSX and Linux platforms. It opens a wide range of new possibilities for the presentation of dynamic multimedia content, where sound plays an important role and the playback of static sound files is not anymore sufficient. The data used by the plug-in that has to be transmitted over the net, is very small in size and thus perfectly suitable for low bandwidth connections. Examples of potential applications are games, adaptive sound backgrounds, interactive sound installations, Web sites, collaborative music on the Web, education and e-learning. The first implementation of the Pd plug-in has been written for a project collaboration with the Catalan theater group \"La Fura dels Baus\".","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127614143","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358109
J. Nützel, M. Kaufmann
The modern audio compression techniques and increased bandwidth in the Internet has dramatically changed the music industry. Music in the 19th century was a service. In the 20th century music became an industrial product. In the 21st century music will be a service again. Illegal sharing services like KaZaA are widely spread. Legal online music services like iTunes from Apple or Napster 2 from Roxio already have been started successfully. Using these systems PC users have access to a huge music database. In contrast to this users of home HiFi systems still miss such online services. The authors give an impression of the future HiFi system they dream of. Like a modern PC the dreamed system, which is currently under development has Internet access and operates with a hard disk. Unlike a PC the HiFi system has a simple user interface. The connection of HiFi system to a special peer-to-peer network provides easy browsing through numerous music titles. The introduced automatic mode allows the user to listen to his favorite music with a one button interaction. Technologies like audio fingerprinting and melody transcription are necessary for future HiFi systems. Some other technologies like recommendation engines and light weighted digital rights management systems are currently under development. The core component of the HiFi system is the content manager. It tries to match the user profile with other existing profiles to send song requests to the connected peer-to-peer network automatically. The described system is closely related to a European research project called semantic HiFi, which is lead by the famous music/acoustic research institute IRCAM. The sharing system is the main contribution of Fraunhofer lDMTand 4FriendsOnly.com AG.
{"title":"Sharing systems for future HiFi systems","authors":"J. Nützel, M. Kaufmann","doi":"10.1109/WDM.2004.1358109","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358109","url":null,"abstract":"The modern audio compression techniques and increased bandwidth in the Internet has dramatically changed the music industry. Music in the 19th century was a service. In the 20th century music became an industrial product. In the 21st century music will be a service again. Illegal sharing services like KaZaA are widely spread. Legal online music services like iTunes from Apple or Napster 2 from Roxio already have been started successfully. Using these systems PC users have access to a huge music database. In contrast to this users of home HiFi systems still miss such online services. The authors give an impression of the future HiFi system they dream of. Like a modern PC the dreamed system, which is currently under development has Internet access and operates with a hard disk. Unlike a PC the HiFi system has a simple user interface. The connection of HiFi system to a special peer-to-peer network provides easy browsing through numerous music titles. The introduced automatic mode allows the user to listen to his favorite music with a one button interaction. Technologies like audio fingerprinting and melody transcription are necessary for future HiFi systems. Some other technologies like recommendation engines and light weighted digital rights management systems are currently under development. The core component of the HiFi system is the content manager. It tries to match the user profile with other existing profiles to send song requests to the connected peer-to-peer network automatically. The described system is closely related to a European research project called semantic HiFi, which is lead by the famous music/acoustic research institute IRCAM. The sharing system is the main contribution of Fraunhofer lDMTand 4FriendsOnly.com AG.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130355615","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 : 2004-09-13DOI: 10.1109/WDM.2004.1358114
Frejman Frejman
Internet has undoubtedly changed the prerequisites for global music distribution once for all. After years of skepticism, clinging to old business models and pirate hunt on P2P networks, the record industry has reluctantly begun to embrace the new channel for marketing and distribution of cultural content. But what do we know about music consumption on P2P networks? Does it coincide with the variety of cultural content in traditional media channels? This work describes the differences in cultural content on P2P networks, concerts and traditional broadcasted media based on comprehensive data on theoretic rage of choice, air play and requested music at P2P services. The study also describes some of the changes in business models that have already taken place. The study concludes among all that legal download services might reduce the present dominance of the big five major record companies in the long run.
{"title":"Radio, concerts and the future of music distribution","authors":"Frejman Frejman","doi":"10.1109/WDM.2004.1358114","DOIUrl":"https://doi.org/10.1109/WDM.2004.1358114","url":null,"abstract":"Internet has undoubtedly changed the prerequisites for global music distribution once for all. After years of skepticism, clinging to old business models and pirate hunt on P2P networks, the record industry has reluctantly begun to embrace the new channel for marketing and distribution of cultural content. But what do we know about music consumption on P2P networks? Does it coincide with the variety of cultural content in traditional media channels? This work describes the differences in cultural content on P2P networks, concerts and traditional broadcasted media based on comprehensive data on theoretic rage of choice, air play and requested music at P2P services. The study also describes some of the changes in business models that have already taken place. The study concludes among all that legal download services might reduce the present dominance of the big five major record companies in the long run.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131134783","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 : 2004-09-13DOI: 10.1109/WEDELMUSIC.2004.10
G. Tummarello, C. Morbidoni, P. Puliti, A. Dragoni, F. Piazza
We present an architecture that provides semantic Web annotations of sound clips described by MPEG-7 audio descriptions. The great flexibility of the MPEG-7 standard makes especially difficult to compare descriptions coming from heterogeneous sources. To cope with this, the architecture would first obtain "normalized" versions of the audio descriptions using different adaptation techniques. Once in a "normalized" format, descriptions can be then projected into uniform and semantically relevant vector spaces, ready to be processed by a variety of well known computational intelligence techniques. As higher semantic results are then available, these can be exported as interoperable (RDF) annotations about the resource that was originally fed into the system. As novel aspect, through the use and interchange of MPEG-7 descriptions, the framework allows building applications (e.g. classificators) which can provide annotations on distributed audio resource sets.
{"title":"From multimedia to the semantic Web using MPEG-7 and computational intelligence","authors":"G. Tummarello, C. Morbidoni, P. Puliti, A. Dragoni, F. Piazza","doi":"10.1109/WEDELMUSIC.2004.10","DOIUrl":"https://doi.org/10.1109/WEDELMUSIC.2004.10","url":null,"abstract":"We present an architecture that provides semantic Web annotations of sound clips described by MPEG-7 audio descriptions. The great flexibility of the MPEG-7 standard makes especially difficult to compare descriptions coming from heterogeneous sources. To cope with this, the architecture would first obtain \"normalized\" versions of the audio descriptions using different adaptation techniques. Once in a \"normalized\" format, descriptions can be then projected into uniform and semantically relevant vector spaces, ready to be processed by a variety of well known computational intelligence techniques. As higher semantic results are then available, these can be exported as interoperable (RDF) annotations about the resource that was originally fed into the system. As novel aspect, through the use and interchange of MPEG-7 descriptions, the framework allows building applications (e.g. classificators) which can provide annotations on distributed audio resource sets.","PeriodicalId":310813,"journal":{"name":"Proceedings of the Fourth International Conference onWeb Delivering of Music, 2004. EDELMUSIC 2004.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132130870","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：