Speaker Dependence verses Independence
Speech recognition software that is dependent on knowledge of the speaker's particular voice characteristics. The software learns the characteristics of the speaker's voice through voice training (or enrollment). This type of system must be trained on a specific user before being able to recognize what has been said. This type of system works well if there is only going to be one user who will be speaking to the system.
Speaker dependent systems are generally able to recognize speech from a variety of contexts (words, phrases). However, speaker independent systems are able to recognize the speech from different users by restricting the contexts of the speech (the words and phrases).
Software that does not require training is speaker independent. These systems are used for automated telephone interfaces. These systems are able to be used by different individuals without training to recognize each persons speech characteristics.
Copyright © 2005
voice-commands.com All Rights
Send questions or comments to
Or use the feedback form: