TERI RESEARCH INC  Providing the Information Advantage...                home.gif (2807 bytes)     

SERVICES       DEFENSE APPLICATIONS      KIOSK-COMMERCIAL       AMERICAN DISABILITIES ACT      back.gif (114 bytes)

Automated Speech Control

Product Desciption

The Automated Speech Control (ASC) product is a speaker independent speech enabling interface system with a defined domain grammar that is developed prior to use. The grammar is capable of handling up to 500 unique words or phrases. The ASC system is designed to use command phrases in lieu of a mouse, keyboard or touch screen, to manipulate the user-defined target application software; such as in windowing pull-down menus, pointing and option selection. It's ideal for moderate sized domains that demand continued excellent speech recognition performance, in high-noise environments of up to 95dBA.

The ASC product is relatively immune to different speaker accent, stress, and style; accepting a wide speaker variation in pronunciation and prosody of speech. Included in the product is a text-to-speech synthesizer providing spoken language feedback of the current status and situation. These ASC qualities are designed to offer a truly hands-free and eyes-free spoken interface capability for public and mobile environments.

The ASC product can easily be integrated within existing HW/SW platforms using generic audio interfaces. Audio I/O options include a noise canceling mic/headset, wireless and hands-free microphone array. TRI's speech enabling interface development and runtime products are unique in the marketplace today. While partial speech enabling solutions are generally available for the speech-enabling interface puzzle, TRI provides a complete system environment for implementation using commercial open-system standards.

Operational Features

Nearly all the speech related engineering and programming has already been accomplished for the customer. The interface between the grammar produced by the development system, the Automatic Speech Recognizer (ASR) and the target application is accomplished through the unique Dialogue Manager (DM). With the generic ASCII text output, all the customer needs to do is to select the communications protocol and media. Solutions exist for Voice XML, TCP/IP, UDP, and serial interfaces.

The communications path is user definable and can be as simple as an intra-computer variable message dialogue path or can be communicated externally through a serial or network path. The target application then processes these tokens and reacts accordingly. Tokens can also be generated in reverse order, when the target application uses the TTS synthesis to annunciate to the user what particular action was taken, recite a message or provide spoken user guidance and assistance.

These capabilities minimize the efforts required by the customers to speech enable their own applications without having to build special hooks within the software. It provides them a hands-free and eye-free means of interacting with their electronic applications in a more natural manner. The technology also uniquely provides these capabilities, for use in high noise environments and with excellent recognition accuracy, both of which are paramount to the successful implementation of speech as an alternate form of input and output.

ASC Packaged Components

Runtime Product Price $395.              Development Product Price $699.