Speech Recognition and Synthesis Component Architecture
The SpeechKit component library includes a speech recognition management class
that provides you a productive way to develop software that listens. Your
application sets properties and invokes methods through the speech recognition
management class. This class handles the low-level functions with speech
recognition engines (i.e., recognizers).
The speech recognition management class, ChantSR, enables you to establish a
session with a recognizer, through which spoken language captured live via a
microphone or from recorded audio can be processed and converted to text. Your
application uses the ChantSR class to manage the activities for speech
recognition on behalf of your application. The ChantSR class manages the
resources and interacts directly with a recognizer application program
interface (API). The ChantSR class supports the following speech APIs:
-
Nuance Dragon NaturallySpeaking,
-
IBM SMAPI (ViaVoice),
-
Microsoft SAPI 4, SAPI 5, Speech Platform, and
-
Nuance VoCon 3200.
Your application receives recognized speech as text and notification of other
processing states through event callbacks.
SpeechKit Architecture for Speech Recognition
The ChantSR class encapsulates all of the technologies necessary to make the
process of recognizing speech simple and efficient for your application.
Optionally, it can save the session properties for your application to ensure
they persist across application invocations.
The ChantSR class simplifies the process of recognizing speech by handling the
low-level activities directly with a recognizer.
You instantiate a ChantSR class object before you want to recognize speech
within your application. You destroy the ChantSR class object and release its
resources when you no longer want to recognize speech within your
application.
Speech Synthesis Management
The SpeechKit component library also includes a speech synthesis (i.e.,
text-to-speech) management class that provides you a productive way to develop
software that speaks. Your application sets properties and invokes methods
through the speech synthesis management class. This class handles the low-level
functions with text-to-speech engines (i.e., synthesizers or voices).
The speech synthesis management class, ChantTTS, enables you to establish a
session with a synthesizer, through which speech is synthesized from text. Your
application uses the ChantTTS class to manage the synthesizer resources on
behalf of the application. The ChantTTS class manages the resources and
interacts directly with a synthesizer application program interface (API). The
ChantTTS class supports the following speech APIs:
Your application receives notification of other processing states through event
callbacks.
SpeechKit Architecture for Speech Synthesis
The ChantTTS class encapsulates all of the technologies necessary to make the
process of synthesizing speech simple for your application. Optionally, it can
save the session properties for your application to ensure they persist across
application invocations.
The ChantTTS class simplifies the process of synthesizing speech by handling
the low-level activities directly with a synthesizer.
You instantiate a ChantTTS class object before you want to synthesize speech
within your application. You destroy the ChantTTS class object and release its
resources when you no longer want to synthesize speech within your
application.
Learn more about Chant SpeechKit »
Related Articles
Where to Buy
