Voice-recognition elevator security system

• US 4,534,056 A
• Filed: 08/26/1982
• Issued: 08/06/1985
• Est. Priority Date: 08/26/1982
• Status: Expired due to Term

• Current Assignee: Inventio AG (Schindler Holding AG)
• Original Assignee: Westinghouse Electric Company LLC (Brookfield Asset Management Incorporated)
• Inventors: Feilchenfeld, Michal M., Byford, Roger G., Quan, Wing C.
• Primary Examiner(s): Kemeny, E. S. Matt
• Application Number:
  US06/411,792
• Time in Patent Office: 1,076 Days
• Field of Search: 381/41-49, 381/110, 187/29 R, 364/513.5, 340/825.31
• US Class Current: 704/272
• CPC Class Codes: B66B 1/468 Call registering systems
• CPC Class Codes: B66B 2201/4623 Wherein the destination is registered after boarding
• CPC Class Codes: B66B 2201/463 Wherein the call is registered through physical contact with the elevator system
• CPC Class Codes: B66B 2201/4646 using voice recognition
• CPC Class Codes: B66B 2201/4676 for checking authorization of the passengers
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

A voice-controlled elevator security system. Access to an elevator system servicing a plurality of landings of a structure is controlled by comparing a voice signal of a potential user of the elevator system with stored voice signals of all authorized users. The comparison is accomplished by first digitizing the potential user'"'"'s voice signal and comparing it, on a bit-by-bit basis, with a digital representation of the voice signals of all authorized users. Various criteria can be established for determining the number of binary bits that must agree to conclude that the potential user is an authorized user. Once this determination has been made, the authorized user can initiate car call signals for those landings to which the authorized user is permitted access.

Claims

1. A voice-controlled elevator security system, including at least one elevator car mounted in a building having a plurality of floors, including a lobby floor, wherein authorized users are each pre-enabled to gain access to a predetermined floor, or floors, of the building from the lobby floor and each authorized user has provided template utterances, said voice-controlled elevator security system comprising:

first memory means for storing template utterances of authorized users, with said template utterances being represented by a plurality of binary bits;

second memory means for storing preselected landings to which each authorized user is permitted access;

digitizing means for digitizing a prospective user'"'"'s spoken utterance, with the user'"'"'s digitized spoken utterance being represented by a plurality of binary bits;

recognition means for comparing the prospective user'"'"'s digitized spoken utterance with at least certain of the template utterances, and for selecting a template utterance having the largest number of binary bits in agreement with the binary bits of the digitized spoken utterance;

threshold means for establishing a threshold limit;

comparator means for comparing the number of binary bits in agreement with said threshold limit and for producing an enable signal when the number of binary bits in agreement exceeds said threshold limit;

said enable signal indicating that the prospective user is the authorized user associated with the selected template;

and call selecting means responsive to said enable signal for enabling a recognized authorized user to gain access to an elevator car at the lobby floor;

said call selecting means further being responsive to said enable signal for enabling the recognized authorized user to direct the accessed elevator car only to an associated pre-enabled floor;

said call selecting means including landing selecting means in the at least one elevator car and up-call selecting means at the lobby floor, wherein activation of the voice controlled elevator security system disables the landing selecting means in the at least one elevator car, except the landing selecting means for the lobby floor, and disables the up-call selecting means on the lobby floor, and wherein identification of the user as an authorized user automatically activates the up-call selecting means on the lobby floor and enables the landing selecting means in the at least one elevator car for those floors to which the authorized user has been pre-enabled to gain access.

2. The voice-controlled elevator security system of claim 1 wherein the means for digitizing the prospective user'"'"'s spoken utterance includes terminal means having a switch, activation of which enables the prospective user to interact with the voice-controlled elevator security system.

3. The voice-controlled elevator security system of claim 2 wherein the terminal means includes display means responsive to the enable signal for indicating that the prospective user is an authorized user.

4. The voice-controlled elevator security system of claim 2 wherein the terminal means includes display means for advising the prospective user when to recite the spoken utterance, said display means being responsive to the comparator means.

5. The voice-controlled elevator security system of claim 4 wherein the comparator means produces a repeat signal when the largest number of binary bits in agreement for a digitized spoken utterance is less than the threshold limit.

6. The voice-controlled elevator security system of claim 5 wherein the display means, in response to the repeat signal, advises the prospective user to repeat the spoken utterance.

7. The voice-controlled elevator security system of claim 1 wherein:

(a) the template utterance for each authorized user includes a plurality of template words maintained in a group,

(b) the recognition means compares the prospective user'"'"'s initial digitized spoken utterance with only a predetermined one of the template words of each group, to identify the group in which this predetermined template word has the largest number of binary bits in agreement with the binary bits of the initial spoken utterance,

(c) the digitizing means digitizes subsequent spoken utterances by the prospective user, and

(d) the recognition means compares each subsequent spoken utterance only with template words from the identified group.

8. The voice-controlled elevator security system of claim 7 wherein the recognition means compares each digitized spoken utterance succeeding the first digitized spoken utterance with only a predetermined one of the template words of the identified group, with the predetermined template word having the same relative position in the group of template words as the digitized spoken word has in a group of spoken utterances.

9. The voice-controlled elevator security system of claim 7 wherein:

(a) the comparator means is responsive to each comparison of the recognition means,

(b) the threshold means establishes a threshold limit for each digitized spoken utterance,

(c) the threshold limit for each utterance following the initial utterance of a prospective user is functionally related to the number of binary bits in agreement for a preceding digitized spoken word of the same user, and

(d) the comparator means only provides an enable signal when all comparisons made relative to a prospective user exceed the associated threshold limit.

10. The voice-controlled elevator security system of claim 9 wherein:

(a) the recognition means also selects a runner-up template word having a second largest number of binary bits in agreement with the binary bits of the digitized spoken utterance, and

(b) the threshold limit established by the threshold means, for each utterance of a prospective user following the initial utterance, is also functionally related to the number of binary bits in agreement in the runner-up template word.

11. The voice-controlled elevator security system of claim 10 wherein the threshold limit for a digitized spoken utterance is functionally related to the difference between the largest number of binary bits in agreement and the second largest number of binary bits in agreement, for a preceding digitized spoken utterance of the same prospective user.

12. The voice-controlled elevator security system of claim 10 wherein the threshold means includes manual means for manually establishing a threshold limit, and wherein the threshold limit for a digitized spoken utterance is functionally related to the difference between the largest number of binary bits in agreement and the second largest number of binary bits in agreement for a preceding digitized spoken utterance of the same prospective user, to the largest number of binary bits in agreement for said preceding digitized spoken utterance of the same prospective user, and to said mutual means.

13. The voice-controlled elevator security system of claim 1 wherein the spoken utterance of an authorized user includes a plurality of spoken words, the template utterance includes a like plurality of associated template words, and including an update operational mode wherein the authorized user can update selected ones of the template words.

14. The voice-controlled elevator security system of claim 1 including a tamper alarm activated when a prospective user fails to qualify as an authorized user.

15. The voice-controlled elevator security system of claim 1 including a train operational mode wherein the authorized user recites an utterance,

the recognition means extracts from the utterance spoken by the authorized user the significant characteristic features thereof and stores the significant characteristic features in the first memory means,

and including a test operational mode wherein each one of the authorized user'"'"'s digitized spoken utterances is compared with a template utterance for determining whether the enable signal is produced.

16. The voice-controlled elevator security system of claim 7 wherein:

(a) the comparator means is responsive to each comparison of the recognition means, and

(b) the threshold means establishes a threshold limit for each digitized spoken utterance as a function of the numerical position of the associated template word in the selected group.

17. The voice-controlled elevator security system of claim 7 wherein:

(a) the comparator means is responsive to each comparison of the recognition means, and

(b) the threshold means establishes a standard threshold limit which is applied to each digitized spoken utterance.

18. The voice-controlled elevator security system of claim 7 wherein:

(a) the comparator means is responsive to each comparison of the recognition means, and

(b) the threshold means establishes a standard threshold limit, and an auxiliary threshold limit which is below the standard threshold limit, with the auxiliary limit being applied to each digitized spoken utterance.

19. The voice-controlled elevator security system of claim 7 wherein:

(a) the comparator means is responsive to each comparison of the recognition means, and

(b) the threshold means establishes a standard threshold limit, and an auxiliary threshold limit which is above the standard threshold limit, with auxiliary limit being applied to each digitized spoken utterance.

20. The voice-controlled elevator security system of claim 7 wherein:

(a) the comparator means is responsive to each comparison of the recognition means, and

(b) the threshold means establishes a standard threshold limit, and an auxiliary threshold limit which is below the standard threshold limit, with said standard and auxiliary limits being applied to selected digitized spoken utterances as a function of the numerical position of the associated template word in the selected group.

21. The voice-controlled elevator security system of claim 7 wherein:

(a) the comparator means is responsive to each comparison of the recognition means, and

(b) the threshold means establishes a standard threshold limit, and an auxiliary threshold limit which is above the standard threshold limit, with said standard and auxiliary limits being applied to selected digitized spoken utterances as a function of the numerical position of the associated template word in the selected group.