|
Variable Speed Speech Synthesis
Navy SBIR 2008.2 - Topic N08-149 NAVAIR - Mrs. Janet McGovern - navair.sbir@navy.mil Opens: May 19, 2008 - Closes: June 18, 2008 N08-149 TITLE: Variable Speed Speech Synthesis TECHNOLOGY AREAS: Information Systems, Human Systems ACQUISITION PROGRAM: PMA205 - Aviation Training Systems OBJECTIVE: Develop a speech synthesis technology that provides realistic and adjustable speed of speech that is intelligible to support a range of fast pace operational and training scenarios. DESCRIPTION: Speech synthesis technology is integrated into training systems to provide team training to individual trainees. However, the current state of the technology does not support the demands of high-speed training scenarios. For example, in Close Air Support training, a Forward Air Controller is required to interact with a pilot as quickly as possible due to the limited time that the aircraft is within range. Current speech synthesis technologies do not allow trainees to interact in a realistic manner in these types of training scenarios. A speech synthesis technology is sought that can be adjusted to provide realistic speed variations for fast paced training scenarios while maintaining intelligibility. PHASE I: Determine the feasibility of developing variable speed speech synthesis technology that allows the user to vary the speed to meet high-speed training scenarios while maintaining intelligibility. Determine and document how speech synthesis technology can be advanced to meet the requirements of variable speed. PHASE II: Develop, test, and validate the new speech synthesis technology. Creatively demonstrate how users can adjust speed variability to meet the needs of a range of training scenarios and the capability of the technology to produce clear and unambiguous speech at various speed levels. PHASE III: Transition effort to commercial developers and government research and development facilities responsible for providing training systems that integrate speech technologies, as well as to operational environments that may benefit from enhanced speech synthesis technologies (e.g. Air Traffic Control for Unmanned Aerial Vehicles). PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: Any organization that utilizes speech synthesis technology to support development of tools to support accessibility (e.g., screen readers for people with visual impairment) and telephone-based systems (e.g., automated call centers). The technology would also be useful to government, industry and academic organizations that develop training systems that require the user to interact with a computer to train team skills. REFERENCES: sinder/thesis/. 3. Speech synthesis evaluation by Nick Campbell; http://www.elra.info/hltevaluationworkshop/img/pdf/Nick%20Campbell.ATR.Speech%20Synthesis%20Evaluation.pdf. 4. Speech Conductor by Christophe d’Alessandro; http://www.enterface.net/enterface05/docs/slides/opening/project6.ppt#256,1,Speech Conductor. 5. Speech Synthesis Markup Language Version 1.1 Requirements by Scott McGlashan; http://www.w3.org/TR/ssml11reqs/. 6. A Perspective on the Next Challenges for TTS Research by Juergen Schroeter, Alistair Conkie, Ann Syrdal, Mark Beutnagel, Matthias Jilka, Volker Strom, Yeon-Jun Kim, Hong-Goo Kang, and David Kapilow; http://www.cstr.ed.ac.uk/downloads/publications/2002/strom02a.pdf. KEYWORDS: Speech Synthesis; Training; Speed Variability; Simulation; Communications; Coordination.
|