Distributed processing in the home using a PC with a wireless speech interface

The Personal Computer is evolving from a purely personal device to one that can support multiple applications in different locations simultaneously. This paper describes how the connectivity and processing capability of the PC can be used in a distributed manner in the home to provide a variety of services like speech activated environmental command and control functions, digital video decoding, Internet telephony and entertainment control. As they are architected today, current PC’s are challenged when trying to perform intensive signal processing tasks while managing several external connections (e.g. dial-up internet) and multiple internal connections (e.g. cordless phone interface) at the same time. We will describe some of these challenges, and what remains to be done to make the PC more capable in undertaking such a multifunctional challenge. 1. USAGE AND APPLICATIONS Currently PCs only provides value to the user when he/she is within arm’s length of the keyboard and mouse. This usage model limits the functionality of the PC to the vicinity of the PC. By using a distributed architecture with a wireless connection, the power of the PC can be accessed from every corner of the home through speech I/O. Command and Control: Traditionally, speech driven command and control applications have been PC application centric, meaning that speech could be used to control ordinary PC applications. You could use voice to control functions normally controlled through the keyboard or mouse. However, with this approach to wireless enabled distributed computing, command and control can be extended to our everyday life and for multiple members of the family. There are two approaches to PC aided command and control that have been experimented with. One is the always listen mode, where the computer is listening for a specific set of commands or key words to initiate an action. A conceptual example of this is the Star Trek computer. The second approach is the 'Push to Speak' mode which requires one to be in close proximity of a portable listening device. With the current state of the technology, much better results have been obtained with the second approach the primary advantages coming from a much better signal strength and the suppression of spurious commands picked up by the microphone. A second usability issue privacy will probably still bias users towards Push to Speak, even when the technology exists to make the Star Trek model work. PC Enhanced Entertainment Center: The days where an entertainment system is a collection of CD players, VCRs, audio-cassette players, and DVD players could be coming to a close. With an Intel® Pentium II processor-based PC equipped with a TV card, all of these capabilities are built into a PC, including soft DVD playback, digital recording/playback of TV shows, and music recording/playback. These features can now be performed with the PC located away from the entertainment center through the use of wireless transmitter/receivers for A/V. The need for multiple remote controls are also eliminated since all of the functions can be voice controlled. The usability issue we run into here is: while speech input is great for choosing what you want, conversational systems have trouble conveying possible options to the user with speech output. The latter shortcoming is readily apparent to all of us who have tried to navigate complex voice-menu options on the telephone. In many cases a small display that complements the Speech I/O would go a long way towards enhancing ease of use.