04.02.2013 Views

MAS.632 Conversational Computer Systems - MIT OpenCourseWare

MAS.632 Conversational Computer Systems - MIT OpenCourseWare

MAS.632 Conversational Computer Systems - MIT OpenCourseWare

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

USES OF VOICE INPUT<br />

Sole IW,1 Cannal<br />

Using Speech Recognition<br />

The previous chapter offered an overview of speech recognition techniques and<br />

the difficulty of identifying the words in a speech signal. This chapter discusses<br />

how speech recognition can be used in applications. It examines the merits as<br />

well as the constraints of using voice input, which limit the classes of applications<br />

for which it is suitable. Because the dominant difficulty with using speech recognition<br />

devices is usually their poor performance, this chapter emphasizes interaction<br />

techniques to manage recognition errors. Finally, several case studies in<br />

applications of voice input are detailed.<br />

Voice input can be suitable to an application for one of several reasons. In some<br />

circumstances, no other input channel may be available due to the lack of an<br />

interface device such as a keyboard or mouse. Even when alternative input<br />

devices are available, speech recognition may be more efficient; we can speak<br />

faster than we write or type. Voice can also be employed effectively when the<br />

user's hands and eyes are occupied with another task.<br />

Regardless of its limitations, voice input is useful when no other input mode is<br />

available or when alternative modes present only limited functionality. For this<br />

reason, speech recognition currently attracts wide interest from the manually­

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!