Speech recognition system with an automatic adaptive learning device
First Claim
1. A speech recognition system comprising:
- a speech-recognition arrangement including means for recognizing speech signals applied to the system and means for applying information signals relating to recognized speech signals to an output of the system, a learning device which interacts with the speech-recognition arrangement during an adaptive learning mode and includes means for adapting the speech-recognition arrangement to the characteristic pronunciation of a given speaker, a keyboard for applying certain words to the speech-recognition arrangement during a learning procedure, a microphone for converting sound signals associated with said certain words and originating from the given speaker to electric speech signals and for applying said speech signals to the speech-recognition arrangement, wherein said speech-recognition arrangement also includes means for determining the progress of the learning procedure in the learning mode, means for displaying details of the learning procedure progress in the learning mode on a display screen, to which the given speaker is to react, characterized in that in normal operation of the system electric speech signals corresponding to a text are fed in to the system via a scannable storage medium in a recording and reproducing device, and wherein electric speech signals which are fed in to the system during the learning procedure of the speech-recognition arrangement are first stored in a storage medium of the recording and reproducing device and subsequent thereto are scanned from the storage medium and fed in to the speech-recognition arrangement, said storage medium having a transmission characteristic that closely approximates the transmission characteristic of said scannable storage medium.
1 Assignment
0 Petitions
Accused Products
Abstract
A speech-recognition system includes a speech-recognition arrangement (1) and a learning device (5) for adapting the speech-recognition arrangement to the characteristic pronunciation of a given speaker during an adaptive learning mode. Certain words are applied during a learning procedure to the speech-recognition arrangement via a keyboard and, in addition, the sound signals associated with these certain words and originating from the given speaker are fed-in via a microphone. The sound signals corresponding to a spoken text are fed into the speech-recognition arrangement via a storage medium which can be scanned by a reproducing device. The reproducing device may be implemented in the form of a recording and reproducing device (7). The sound signals which are fed in to the system during a learning procedure of the speech-recognition arrangement are first recorded onto the storage medium and immediately thereafter are scanned from the storage medium and are fed into the speech-recognition arrangement.
13 Citations
3 Claims
-
1. A speech recognition system comprising:
- a speech-recognition arrangement including means for recognizing speech signals applied to the system and means for applying information signals relating to recognized speech signals to an output of the system, a learning device which interacts with the speech-recognition arrangement during an adaptive learning mode and includes means for adapting the speech-recognition arrangement to the characteristic pronunciation of a given speaker, a keyboard for applying certain words to the speech-recognition arrangement during a learning procedure, a microphone for converting sound signals associated with said certain words and originating from the given speaker to electric speech signals and for applying said speech signals to the speech-recognition arrangement, wherein said speech-recognition arrangement also includes means for determining the progress of the learning procedure in the learning mode, means for displaying details of the learning procedure progress in the learning mode on a display screen, to which the given speaker is to react, characterized in that in normal operation of the system electric speech signals corresponding to a text are fed in to the system via a scannable storage medium in a recording and reproducing device, and wherein electric speech signals which are fed in to the system during the learning procedure of the speech-recognition arrangement are first stored in a storage medium of the recording and reproducing device and subsequent thereto are scanned from the storage medium and fed in to the speech-recognition arrangement, said storage medium having a transmission characteristic that closely approximates the transmission characteristic of said scannable storage medium.
- View Dependent Claims (2)
-
3. A speech-recognition system comprising:
a speech-recognition arrangement for recognizing speech signals applied to the system and for applying information relating to recognized speech signals to an output, a learning device which interacts with the speech-recognition arrangement in an adaptive learning mode of the speech-recognition arrangement and, in order to adapt the speech-recognition arrangement to a characteristic pronunciation of a given speaker, comprises means including a microphone for applying spoken words to the system in the learning mode via a recording and reproducing device having a storage device, means including the speech-recognition arrangement and the learning device for determining the progress of a learning operation in the learning mode, display means for displaying details of the progress in the learning mode on a display screen, to which the given speaker is to react, the recording and reproducing means recording electric sound signals corresponding to the spoken words on the storage device and reproducing the electric sound signals recorded in a direct reproduce after recording mode of operation as a part of the learning operation, wherein, during normal operation of the system electric speech signals are fed in to the system via a scannable storage medium in a further recording and reproducing device, said scannable storage medium having a transmission characteristic that closely approximates the transmission characteristic of the storage device.
Specification