Client Application Program Interface for Continuous Speech Recognition System
Original Publication Date: 1994-Apr-01
Included in the Prior Art Database: 2005-Mar-26
Booth, BJ: AUTHOR [+2]
The following describes a client application program interface for the IBM Continuous Speech Recognition System (ICSRS).
Client Application Program Interface for Continuous
describes a client application program interface
for the IBM Continuous Speech Recognition System (ICSRS).
application program interacts with ICSRS in a client-server
fashion, where the application is the client and ICSRS is the server.
with ICSRS is called a conversation.
initiated with srStartConversation and concluded with
srEndConversation. Within a conversation are a series of recognition
requests. A recognition request starts with srListen which tells
ICSRS to begin listening to speech. A recognition request is
completed with a call to srGetSpokenWords which retrieves the
recognizes speech within a frame of reference called a
context. Contexts are created in advance using the ICSRS
task-building utility. The input to task building is a set of
sentences in Backus-Naur format that comprise the recognizable
utterances of the context. Thus a context is a set of files produced
by the task-building utility.
made known to the conversation by defining them
(i.e., specifying that the context may be used in a recognition
request). A context is defined using the srDefineContext function.
A number of contexts may be defined for a conversation. From the
contexts defined to the conversation, only one is in use per
recognition request. To use a defined context for a recognition
request, you activate it. A context is activated using the
srActivateContext function. One context must be active for each
recognition request, and it may be changed from request to request.
It is advantageous to use a series of small contexts (and switch
between them for recognition requests) because the recognition is
faster on smaller contexts. A con...