Speech recognition using telephone call parameters

Details Speech recognition using telephone call parameters Speech recognition using telephone call parameters

1998-02-05

2002-11-19

Tsang, Fan (Department: 2645)

Telephonic communications

Audio message storage, retrieval, or synthesis

Voice activation or recognition

C379S088020, C704S231000, C704S246000, C704S255000

Reexamination Certificate

active

06483896

ABSTRACT:

FIELD OF THE INVENTION
The present invention is directed to a speech recognition system. More particularly, the present invention is directed to a speech recognition system that uses telephone call parameters to increase its accuracy.
BACKGROUND OF THE INVENTION
Speech recognition systems are increasingly being used to translate human spoken words or utterances directly into their written equivalent and meaning. Speech recognition systems can avoid the need for these spoken words to be manually entered into a computer, or to be recognized by a human. Therefore, speech recognition systems are desirable for many businesses because they allow employees to perform other tasks.
However, speech recognition systems can provide inaccurate results. An exact correspondence between a spoken word and a recognized word is difficult to attain due to, for example, the deterioration of speech signals that routinely occurs over conventional telephone lines and the different ways the same words are pronounced by different users. In order to compensate for inaccuracies, many speech recognition systems used by businesses must request that a user pronounce the word multiple times, or be subject to various confirmation routines. I his can be time consuming and frustrating to the user.
Based on the foregoing, there is a need for a speech recognition system that has an increased recognition accuracy compared to known speech recognition systems without requiring additional input from the user.
SUMMARY OF THE INVENTION
One embodiment of the present invention is a speech recognition system for recognizing a telephone call parameter dependent word received during a telephone call. The recognition system extracts a telephone call parameter (e.g., the telephone number from where the telephone call originated, the time of day, etc.) from the telephone call and generates a probable word set from the telephone call parameter. The probable word set includes at least one telephone call parameter dependent word. Further, the recognition system receives a speech signal and generates one or more word choices from the speech signal. The recognition system then selects, based on the probable word set, one of the generated word choices as the recognized telephone call parameter dependent word.
By using a telephone call parameter to recognize a received speech signal, the recognition accuracy in the present invention is improved without requiring any additional user input.


REFERENCES:
patent: 5241619 (1993-08-01), Schwartz et al.
patent: 5524169 (1996-06-01), Cohen et al.
patent: 5638425 (1997-06-01), Meador, III et al.
patent: 5644680 (1997-07-01), Bielby et al.
patent: 5748840 (1998-05-01), La Rue
patent: 5867562 (1999-02-01), Scherer
patent: 5960063 (1999-09-01), Kuroiwa et al.
patent: 5995929 (1999-11-01), Gupta
patent: 6122361 (2000-09-01), Gupta

Affiliated with

Also associated with

Rating

Speech recognition using telephone call parameters does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech recognition using telephone call parameters, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition using telephone call parameters will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2968942