Chant ProfileKit

Maximize speech recognition accuracy by ensuring end users have completed training sessions with the recognizer. Speaker training—even for command and grammar-based recognition—is essential for accuracy.

A recognition profile is a collection of information used by a speech recognition engine to increase its recognition accuracy for a specific individual's voice and environment.

A speech recognition engine saves training and background noise information to use in recognizing speech. Some speech recognition engines, such as Microsoft's Recognizer, capture and save information over time to adapt the profile for optimum speech recognition accuracy.

What is Profile Management?

Profile management enables you to:

  • create and delete speech recognition profiles,
  • train speech recognition profiles, and
  • backup and restore speech recognition profiles.

Applications benefits include:

  • enhanced speech recognition accuracy,
  • added flexibility to adapt to different acoustical environments, and
  • expanded reliability to recover from system errors.

What is ProfileKit?

Chant ProfileKit handles the complexities of managing profiles and persisting them in files for backup and recovery.

It simplifies the process of managing profiles for Nuance Dragon NaturallySpeaking, Microsoft SAPI 5, Microsoft Speech Platform, and Nuance VoCon recognizers. You can backup and restore, activate, create, delete, and train profiles as needed within your application to adapt to the end user.

ProfileKit includes C++, C++Builder, Delphi, Java, .NET Framework, and Silverlight class library formats to support all your programming languages and sample projects for popular IDEs—such as the latest Visual Studio from Microsoft and RAD Studio from Embarcadero.

The class libraries can be integrated with 32-bit and 64-bit applications.

Profile Management Component Architecture

The ProfileKit class library includes a profile management class that provides you a simple way to create, delete, train, backup and restore speaker profiles. Your application can integrate speaker training, backup, and recovery as part of its speech recognition administrative features.

The profile management class, ChantPM, enables you to select or create a speaker, train it, and optionally persist the profile (i.e., training) to a binary file. Your application can import the training to restore a profile or define a user on a new system. In addition the archived profile can be self extracting or self installing file. The ChantPM class supports the following recognizers:

Your application receives backup and restore progress notifications through event callbacks.

ProfileKit Architecture for Profile Management

The ChantPM class encapsulates all of the technologies necessary to make the process of managing profiles simple and efficient for your application. Optionally, it can persist the profile to a self extracting archive for portability across systems.

ProfileKit Architecture for Profile Management

The ChantPM class simplifies the process of managing profiles by handling the low-level activities directly with the speech recognition engine application program interfaces (API).

You instantiate a ChantPM class object before you want to manage a profile within your application. You destroy the ChantPM class object and release its resources when you no longer want to manage a profile within your application.

Feature Summary

The goal of profile management is to maximize speech recognition accuracy. With ProfileKit you can:

  • Create and delete speaker profiles on demand;
  • Train speaker profiles; and
  • Backup and restore speaker profiles for ensuring maximum recognition accuracy and reliability.

Chant ProfileKit handles the complexities of managing and persisting speaker profiles. This allows your application to enhance the quality of speech recognition and offer administrative features for maintaining speaker profiles.

Recognizers provide speaker training via built-in dialogs and/or custom training via API calls. ProfileKit supports the following recognizers and speaker training options:

RecognizerSpeech APITraining DialogsCustom Training
Microsoft SAPI 5 (all languages)SAPI 5YesYes
Microsoft Speech Platform (all languages)MSPYesYes
Nuance Dragon NaturallySpeaking (all languages)Dragon APIYesNo
Nuance VoCon 3200 V2 (all languages)VoCon 3200 V2NoYes
Nuance VoCon 3200 V3 (all languages)VoCon 3200 V3NoYes
Nuance VoCon 3200 V4 (all languages)VoCon 3200 V4NoYes

Recognizers support speaker profile archiving via built-in dialogs or via API calls. ProfileKit supports the following recognizers and speaker profile archive options:

RecognizerSpeech APIArchiving DialogsAPI
Microsoft SAPI 5 (all languages)SAPI 5NoYes
Microsoft Speech Platform (all languages)MSPNoYes
Nuance Dragon NaturallySpeaking (all languages)Dragon APIYesNo
Nuance VocCon 3200 V2 (all languages)VoCon 3200 V2NoYes
Nuance VocCon 3200 V3 (all languages)VoCon 3200 V3NoYes
Nuance VocCon 3200 V4 (all languages)VoCon 3200 V4NoYes

Within Chant Developer Workbench, you can:

  • Create and delete speaker profiles;
  • Enumerate speaker profiles; and
  • Invoke recognizer built-in speaker training;
  • Design and test custom speaker training;
Built-in Speaker Training
Built-in Speaker Training: Enumerate and train speech recognition profiles with recognizer built-in speaker training.
Custom Speaker Training
Custom Speaker Training: Enumerate and train speech recognition profiles with custom speaker training.

ProfileKit License

You may explore the capabilities of Chant ProfileKit for 30 days. To continue to use the product after 30 days, you must purchase a license for the software or stop using the software and remove it from your system.

A valid purchased license gives you the right to construct executable applications that use the applicable class library and distribute it with executable applications without royalty obligations to Chant.

The Chant ProfileKit license is a single end-user license. Each developer who installs and uses ProfileKit to develop applications must have their own license.

ProfileKit class library names vary by platform: Windows 32-bit and 64-bit. This helps ensure the correct library is deployed with your application.

You may purchase a license for Chant ProfileKit on-line at the Chant store or through your preferred software reseller.

ProfileKit System Requirements

Development Environment

  • Intel processor or equivalent,
  • Microsoft Windows 10 , 8, 7,
  • 120 MB of hard drive space,
  • CD-ROM drive,
  • VGA or higher-resolution monitor,
  • Microsoft SAPI 5, Nuance Dragon NaturallySpeaking, or Nuance VoCon 3200 recognizer,
  • C++, C++Builder, Delphi, Java, .NET Framework, or Silverlight environment, and
  • close-talk microphone.

Where to Buy

Order Chant ProfileKit online at the Chant store

Order Chant ProfileKit online at the Chant store or through your preferred software reseller.

Try It Buy It