A speech recognition system includes a user profile to store acoustic data and a corresponding text transcript. A speech recognition ("SR") server downloads the acoustic data and the corresponding text transcript that are stored in the user profile. A speech recognition engine is included to adapt an acoustic model based on the acoustic data.
A speech dialogue system (SDS) is provided for carrying out a speech dialogue with a user to control an electronic device. The SDS includes a speech dialogue interruption unit for interrupting the speech dialogue and a speech dialogue continuation unit for continuing the interrupted speech dialogue. The system provides a method of conducting the speech dialogue between the speech dialogue system and a user. The method provides the steps of interrupting the speech dialogue upon receipt of a predetermined pause command from the user or from an electronic device. The method continues the speech dialogue with the speech dialogue system when the user or the electronic device provides a predetermined continuation command to the SDS. The method further allows the canceling of the speech dialogue when the user provides a predetermined cancellation command to the SDS.
A system is disclosed for controlling at least one electronic device. Each electronic device may have at least one control key. The system for controlling the electronic device may include a speech dialog system that controls the electronic device. The speech dialog system may be activated upon an operation of one or more control keys of the electronic device.
