You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
35 lines
2.3 KiB
35 lines
2.3 KiB
Introduction
|
|
|
|
In this book, we are concerned with describing a successful approach to the con-
|
|
version of unrestricted English text to speech. Before taking up the details of this
|
|
process, however, it is useful to place this task in context. Over the years, there
|
|
has been an increasing need for speech generated from computers. In part, this has
|
|
been due to the intrinsic nature of text, speech, and computing. Certainly speech is
|
|
the fundamental language representation, present in all cultures (whether literate or
|
|
not), so if there is to be any communication means between the computer and its
|
|
human users, then speech provides the most broadly useful modality, except for
|
|
the needs of the deaf. While text (considered as a string of conventional symbols)
|
|
is often considered to be more durable than speech and more reliably preserved,
|
|
this is in many ways a manifestation of relatively early progress in printing tech-
|
|
nology, as opposed to the technology available for storing and manipulating
|
|
speech. Furthermore, text-based interaction with computers requires typing (and
|
|
often reading) skills which many potential users do not possess. So if the increas-
|
|
ingly ubiquitous computer is to be useful to the largest possible segment of society,
|
|
interaction with it via natural language, and in particular via speech, is certainly
|
|
necessary. That is, there is a clear trend over the past 25 years for the computer to
|
|
bend increasingly to the needs of the user, and this accommodation must continue
|
|
if computers are to serve society at large. The present search for expressive pro-
|
|
gramming languages which are easy to use and not prone to error can be expected
|
|
to lead in part to natural language interaction as the means best suited to human
|
|
users, with speech as the most desirable mode of expression.
|
|
|
|
1.1 Constraints on speech synthesis
|
|
|
|
It is clear, then, that speech communication with computers is both needed and
|
|
desirable. Within the realm of speech output techniques, we can ask what the na-
|
|
ture of these techniques is, and how they are realized. In order to get a view of the
|
|
spectrum of such procedures, it is useful to consider them as the result of four dif-
|
|
ferent constraints which determine a design space for all possible speech output
|
|
schemes. Each technique can then be seen as the result of decisions related to the
|
|
impact of each of the four constraint areas.
|