Performs Speech Synthesis and Speech Recognition. Branching occurs when speech recognition is successful in matching what the user says to words or phrases in one of the Red Output Ports.
Examples Tutorial 1 Tutorial 2 Tutorial 3 Tutorial 4
Tutorial 5 Tutorial 6Tutorial 7 Tutorial 8 Tutorial 9 Tutorial 10
Tutorial 11 Tutorial 12Tutorial 13 Tutorial 14
Summary
Use the Generic Object to make the computer speak or to provide branching based on speech recognition. In the example below, the Generic Object asks "What is two plus two?" If the user says "four" the dialogue will branch to the left, if the user says anything else (*any) the dialogue will branch to the right.
Speech Synthesis:
Control the computer’s voice using text. The available voices include several languages, dialects and genders. A recorded voice may also be used. Access speech synthesis controls from the Generic Object’s properties menu. (Double click the icon)
Speech recognition:The Toolkit speech recognition system tries to match what the user says to words in the recognition ports. In the above diagram, the dialogue can branch one of two ways: to the left if the user says "Four" and to the right if the user says anything else. The recognition uses ‘word spotting’. For example, the recognizer would spot the "four" within the response, "I think four is the correct answer."
Unlike large vocabulary speaker dependent recognizers like those used in word processors, the Speech Toolkit allows you to select from several small vocabulary, speaker independent recognition systems that do not need to be trained on your voice. The Toolkit’s speech recognition does not create a direct text transcription, but rather the uses speech recognition and word spotting to control the flow of the dialog through branching at each Generic Object.
Creating a Speech Synthesis Prompt
Select the TTS ( text to speech) tab to enter text for the computer to speak.
Select the Recorded tab to pre-process the TTS or use your own voice.
See the
tutorials or the Properties guide to make TTS and recorded speech prompts
Kal, I’ll send along the individual tab description docs
Each object’s preferences window has a subset of these tabs.
TTS Edit the text to speech
Recorded Edit recorded speech or pre-process TTS prompts
Recognition Edit speech recognition settings, change recognizers, repair dialogs.
DTMF Edit touch tone telephony settings
Misc Edit miscellaneous settings
On Enter Create a Tcl/TK script to be run when the dialog enters the object
On Enter Create a Tcl/TK script to be run when the dialog exits the object
Tucker-Maxon Edit Tucker-Maxon Package settings
Use Select TTS (text to speech) or recorded voice
Face Select from available user defined and default face configurations
Creating Speech Recognition:
Getting Started
Double Click a RED PORT
or Right Click the RED PORT and select OPEN
Edit Word vocabulary
Modifying the word vocabulary
To modify an existing word vocabulary you must explicitly click the "Update All" button to
for the changes to take effect. Click OK to save and close
Manually editing phonetic pronunciation
When you click OK to Close, the system automatically generates a phonetic pronunciation for your words and phrases. You can manually edit these phonetic pronunciations using WorldBet. Do Not click "Update All" when manually editing the phonetic pronunciation as this will re-build the pronunciation from the words on the left.
Adding Output Ports
Right Click the Icon and select Add Port
Deleting Output Ports
Right Click RED PORT you wish to delete and select Delete
Properties
Opens the properties window for the action box
Add Port
Creates an additional RED Speech Recognition Port for branching
Cut
Deletes the object and copies it to the clip board
Copy
Copies the object to the clip board
Delete
Deletes the object
Rename
Renames the object as it appears on the canvas