S
Stephane H. Maes
Researcher at Hewlett-Packard
Publications - 313
Citations - 17801
Stephane H. Maes is an academic researcher from Hewlett-Packard. The author has contributed to research in topics: Speaker recognition & Speaker diarisation. The author has an hindex of 65, co-authored 289 publications receiving 17318 citations. Previous affiliations of Stephane H. Maes include Princeton University & Business International Corporation.
Papers
More filters
Patent
A portable information and transaction processing system and method utilizing biometric authorization and digital certificate security
Stephane H. Maes,Jan Sedivy +1 more
TL;DR: A portable client PDA with a touch screen or other equivalent user interface and having a microphone and local central processing unit (CPU) for processing voice commands and for processing biometric data to provide user verification is presented in this article.
Patent
Conversational networking via transport, coding and control conversational protocols
TL;DR: In this article, a system and method for implementing conversational protocols for distributed conversational networking architectures and/or distributed conversations, as well as real-time conversational computing between network-connected pervasive computing devices and servers over a computer network is described.
Patent
System and method for multi-modal focus detection, referential ambiguity resolution and mood classification using multi-modal input
Stephane H. Maes,Chalapathy Neti +1 more
TL;DR: In this paper, a method for performing focus detection, ambiguity resolution and mood classification in accordance with multi-modal input data, in varying operating conditions, in order to provide an effective conversational computing environment (418, 422) for one or more users (812).
Patent
Universal IP-based and scalable architectures across conversational applications using web services for speech and audio processing resources
TL;DR: In this paper, the authors present systems and methods for building distributed conversational applications using a Web services-based model where speech engines (e.g., speech recognition) and audio I/O systems are programmable services that can be asynchronously programmed by an application using a standard, extensible SERCP (speech engine remote control protocol), to provide scalable and flexible IP-based architectures that enable deployment of the same application or application development environment across a wide range of voice processing platforms and networks/gateways.
Patent
Conversational computing via conversational virtual machine
Daniel M. Coffman,Liam David Comerford,Steven Vincent Degennaro,Edward A. Epstein,Ponani S. Gopalakrishnan,Stephane H. Maes,David Nahamoo +6 more
TL;DR: A conversational computing system that provides a universal coordinated multi-modal conversational user interface (CUI) across a plurality of conversationally aware applications (i.e., applications that'speak' conversational protocols) and conventional applications is described in this paper.