Features

For the latest version and support, please check the Cloudgarden site regularly.

• Support for large range of speech engines
All fully-compliant SAPI4 and SAPI5 recognizers and synthesizers should work with this implementation. This opens up a large number of speech engines to the Java developer. In virtually all situations, the engine type is transparent to the implementation, but when needed the engine type (ie SAPI4 or 5) can be discovered and the situation handled accordingly. More details here.
• Full implementation of Sun's JSAPI 1.0 specification
The implementation of Sun's specification provided here is as complete as possible, allowing recognition grammars to be specified in Sun's Java Speech Grammar Format, and speech synthesis to be controlled in-line using Sun's Java Speech Markup Language tags. The few differences and the several additions (outside of the core JSAPI specification) are described in detail here , and outlined below.
• Graphical User Interface additions
Classes in the com.cloudgarden.speech and com.cloudgarden.speech.userinterface packages allow customizable Dialogs to be displayed which list all available engines, profiles and voices and allow the user to test and select them. Lip-sync events are also captured from synthesizers and can be displayed using a "Mouth" which extends the java.awt.Component class so can be superimposed on other Components. More details here.
• Audio data redirection additions
An interface with Sun's Java Media Framework, and with the javax.sound.sampled package, is provided which allows the speech engines to send and receive audio data in compressed formats (such as MP3) to and from files and over networks. More details here.
• Feedback on recognition confidence
Recognition results are given with values representing the confidence with which they have been recognized by the speech engine, allowing a certain degree of feedback to provided in language-training applications. More details here.
• Recognized utterances can be saved to WAVE files
The AudioClip returned from the FinalResult.getAudio method can be cast into a com.cloudgarden.speech.CGResultAudioClip, whose saveToFile(String fileName) method can be called to save the audio data to a WAVE file.
• Guessing of current speaker
Only applies to SAPI4 engines - the CGEngineProperties.allowGuessingOfSpeaker can be used to allow the Recognizer to change the current SpeakerProfile based on who it thinks is speaking. More details here.
• Lip-Sync events for speech synthesis
Lip-sync events are now detected from Synthesizers and CGSpeakableEvents broadcast to CGSpeakableListeners, which can then display the current shape of a mouth using the com.cloudgarden.speech.userinterface.Mouth Component. More details here.
• Can be used in Applets and Plugins (in suitable browsers)
Since the implementation works with the Java 1.1 specification, it can run inside the native JVMs of suitable browsers after proper installation and without the need to install Sun's JRE. More details here.