SpeechStudio Suite is a complete set
of tools, utilities, and controls for rapidly constructing, integrating, or
prototyping speech and telephony applications. Developers can quickly
voice-enable desktop and Tablet PC applications with speech-recognition,
dictation, text-to-speech, audio recording, and playback. SpeechStudio's built-in support for TAPI telephony devices enables many
common scenarios, including auto-answer, dial-out, touch-tone, and voice
mail applications.
SpeechStudio
Lexicon Developer allows developers to create and distribute custom
vocabularies for speech recognition and text-to-speech.
SpeechStudio Profile Developer allows
developers to create, capture, and deploy speech-recognition profiles,
saving time and training costs. Lexicon Developer and Profile
Developer are available individually or as part of SpeechStudio Suite.
SpeechStudio TAPI Control connects
telephony devices to SAPI 5 audio streams for both text-to-speech and speech
recognition. Includes a .Net C# example.
SpeechStudio
Components for SAPI 5 extend SAPI with ActiveX components for lexicons, pronunciations,
and phonemes, a programmatic interface to training sessions and the Speech
Control Panel, and grammars for recognizing integers, ordinals, and real
numbers.
SpeechStudio Lexicon
Builder creates custom
vocabularies and pronunciations for Microsoft text-to-speech, speech
recognition, Office XP, or any SAPI 5 speech engine. Lexicon Builder finds new words by analyzing existing documents and comparing the results to the Office XP dictionary,
and its wizard helps you create the right phoneme strings for a custom dictionary that is tuned
specifically for your vocabulary. Developers can use Lexicon Builder to
create custom pronunciations for their applications.
SpeechStudio Profile Manager
software enables you to
create, delete, train, modify, backup and restore speech recognition profiles.
You can quickly and easily copy profiles between computers, eliminating the need
to train each system. You can backup your user profile against system failures
or degradation of the speech-recognition system.
|
