Grant: Collaborative Research and Development Grants
University of Toronto
$70,933.00
Distributed Multimodal and Multimedia Services
EF 2009-10
Résumé
Recently much work has been done to promote voice-activated interactive voice/response (IVR) systems. At the moment, as there is no developed application, the flow of calls are managed off-line to play the appropriate prompts based on the customer interaction with the system. Current voice recognition experiences are limited to the conventional interactive voice/response (IVR) media incorporating automatic speech recognition, statistical language models, and dialog manager technologies. These technologies would have to be revisited to factor in other inputs and technologies to provide a richer, more versatile, and a more robust User Interface (UI) compared to traditional unimodal speech services. Multimodal, multimedia (MM) extension of IVR systems is a natural migration path for offering the opportunity to adapt the customer experience to the actual terminal capabilities of the access device. The proposed research will develop a new generation of virtual agents that are capable of multimodal/multimedia interactions.
The proposed research activity has two parts that are complementary factors in designing and developing a comprehensive solution to incarnate new generations of interactive avatars that are responsive to multimodal/multimedia communications. The first part of the research encompasses methods and algorithms used as enabler for multimodal user/server interactions. The other part includes all methods and query passings among a set of intelligent multimodal servers. To design the first fragment, we will use recent developments in sparse-space signal processing and develop novel algorithms for feature extraction and design interactive multimodal client/server applications. The second part of the research will be based on peer-to-peer (P2P) networking in overlay networks that can deal with a diverse set of substrate network technologies. We will develop a protocol solution, called cross-substrate advertisement, that can maintain a single overlay network over multiple substrate networks.
Programme
Collaborative Research and Development Grants
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
372257-2008
Name nom
Valaee, Shahrokh
Department département
Electrical and Computer Engineering, Edward S. Rogers Sr. Department of
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2008
Award amount
70933
Program id
CRDPJ
Program nane en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
804
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Communication systems and services (planning, organization, services)
Area of application fr
Systèmes et services de communications (planification, organisation et services)
Research subject code
2508
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Communications networks
Research subject fr
Réseaux de télécommunications
Partie
1
Nb partie
2
Application title
Distributed Multimodal and Multimedia Services
Keyword
NA
Application summary
Recently much work has been done to promote voice-activated interactive voice/response (IVR) systems. At the moment, as there is no developed application, the flow of calls are managed off-line to play the appropriate prompts based on the customer interaction with the system. Current voice recognition experiences are limited to the conventional interactive voice/response (IVR) media incorporating automatic speech recognition, statistical language models, and dialog manager technologies. These technologies would have to be revisited to factor in other inputs and technologies to provide a richer, more versatile, and a more robust User Interface (UI) compared to traditional unimodal speech services. Multimodal, multimedia (MM) extension of IVR systems is a natural migration path for offering the opportunity to adapt the customer experience to the actual terminal capabilities of the access device. The proposed research will develop a new generation of virtual agents that are capable of multimodal/multimedia interactions.
The proposed research activity has two parts that are complementary factors in designing and developing a comprehensive solution to incarnate new generations of interactive avatars that are responsive to multimodal/multimedia communications. The first part of the research encompasses methods and algorithms used as enabler for multimodal user/server interactions. The other part includes all methods and query passings among a set of intelligent multimodal servers. To design the first fragment, we will use recent developments in sparse-space signal processing and develop novel algorithms for feature extraction and design interactive multimodal client/server applications. The second part of the research will be based on peer-to-peer (P2P) networking in overlay networks that can deal with a diverse set of substrate network technologies. We will develop a protocol solution, called cross-substrate advertisement, that can maintain a single overlay network over multiple substrate networks.