Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
1999-11-12
2003-04-29
Banks-Harold, Marsha D. (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S233000, C704S226000
Reexamination Certificate
active
06556968
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to data terminals with voice recognition function and voice recognition system, more particularly, to portable data terminal and voice recognition system having a voice recognition function. The term “voice recognition” is used herein to refer to what is more commonly known as “speech recognition” or “word recognition” that denotes what is being said, rather than who is speaking.
Recently, in a portable telephone set, a voice recognition function is utilized without operating ten keys. The voice recognition is performed for the pronounced name of the opposite side destination through a microphone.
In such a portable telephone set, a voice to be recognized is preliminarily registered through the microphone. When a voice which is recognized to be the same as the registered voice is generated, a call making or like operation is performed in response to this voice.
Such a portable telephone set can be used in any place as its service area, so that it may be used in noisy places or high noise level places. In such a case, ambient noise or noise sounds may be added to voice inputted from the microphone when making a call or the like. This may result in failure of detection of coincidence of the inputted voice with a preliminarily registered voice or erroneous judgment that the inputted voice is coincident with a different voice.
To solve such a problem, it is conceivable to register words for the voice recognition in a high noise level place. Also, it is conceivable to end the voice recognition process when it is judged that noise is inputted.
By adopting either one of the above two methods, it is possible to prevent erroneous voice recognition even in the case when the ambient noise level is high. However, it is impossible to prevent erroneous voice recognition under the noisy condition after the start of the voice recognition as a result of bringing the microphone of the portable telephone set to be closer to the mouth or bringing the loudspeaker into contact with an ear for listening to the voice from the loudspeaker. In the latter case, it is necessary to start the voice recognition once again by executing a voice recognition starting operation.
SUMMARY OF THE INVENTION
An object of the present invention is to solve the above problems and provide a portable data terminal and voice recognition system having an improved voice recognition function.
Another object of the present invention is to provide a portable data terminal and voice recognition system capable of improving the erroneous voice recognition possibility in the voice recognition.
A further object of the present invention is to provide a portable data terminal and voice recognition system capable of preventing erroneous voice recognition due to suddenly occurring noise or noise generated by taking hold of the terminal afresh.
According to an embodiment of the present invention, there is provided a portable data terminal comprising: a microphone for inputting voice; a memory for registering voice recognition words in advance; and voice recognition means for executing voice recognition with respect to voice inputted from the microphone and reading out a voice recognition word corresponding to the inputted voice; voice recognition being prohibited when noise other than voice is detected at the time of the voice recognition.
The portable data terminal further comprises registering means for preliminarily registering patterns for pulling in the noise.
The portable data terminal further comprises means for informing, when noise other than the voice is detected, that the voice recognition is prohibited.
In the portable data terminal, the detection of noise other than the voice is done within a predetermined period of time from the instant of the voice recognition start.
According to another embodiment of the present invention, there is provided a voice recognition system for recognizing an input sound in which words to be recognized and predetermined noise sounds are preliminary registered as recognition subjects and noise, and when the input sound is recognized as the noise, the recognition is not performed or the recognition result is ignored.
According to other embodiment of the present invention, there is provided a voice recognition system for recognizing an input sound in which words to be recognized and predetermined noise sounds are preliminary registered as recognition subjects and noise, the recognition process is performed after lapse of a predetermined time, and when the input sound is recognized as the noise, the recognition is not performed or the recognition result is ignored.
In the voice recognition system, when the input sound is recognized as the noise, the recognition process is again performed and when the input sound is recognized as the noise, its recognition result is displayed or produced in voice.
In the voice recognition system, the noise recognition is performed within a predetermined time.
Other objects and features will be clarified from the following description with reference to attached drawings.
REFERENCES:
patent: 5764852 (1998-06-01), Williams
patent: 6324499 (2001-11-01), Lewis et al.
patent: 62-91047 (1987-04-01), None
patent: 62-150295 (1987-07-01), None
patent: 2-56600 (1990-02-01), None
patent: 2-83593 (1990-03-01), None
patent: 4-58297 (1992-02-01), None
patent: 4-181846 (1992-06-01), None
patent: 5-48702 (1993-02-01), None
patent: 7-283857 (1995-10-01), None
patent: 8-211892 (1996-08-01), None
patent: 11-194797 (1999-07-01), None
Banks-Harold Marsha D.
Harper V. Paul
NEC Corporation
Young & Thompson
LandOfFree
Data terminal with speech recognition function and speech... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Data terminal with speech recognition function and speech..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Data terminal with speech recognition function and speech... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3065456