Voice recognition system

• US 4,581,755 A
• Filed: 10/27/1982
• Issued: 04/08/1986
• Est. Priority Date: 10/30/1981
• Status: Expired due to Term

• Current Assignee: Nippon Electric Company Limited (NEC Corporation)
• Original Assignee: Nippon Electric Company Limited (NEC Corporation)
• Inventors: Sakoe, Hiroaki
• Primary Examiner(s): KEMENY, EMANUEL
• Application Number:
  US06/436,978
• Time in Patent Office: 1,259 Days
• Field of Search: 381/41-44, 364/513.5
• US Class Current: 704/247
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates

Abstract

There is provided a voice recognition system comprising a standard pattern memory in which a voice pattern of a predetermined word is stored as a positive reference pattern and also voice patterns of words similar to but different from the first-mentioned word are stored as negative reference patterns, a pattern comparator for calculating dissimilarities of an input voice pattern with respect to the positive reference pattern and negative reference patterns, and a discriminator for providing a coincidence confirmation output signal when the dissimilarity with respect to the positive reference pattern is less than a predetermined threshold value and less than the dissimilarities with respect to the negative reference patterns while otherwise rejecting the result of recognition.

Claims

1. A voice recognition system comprising a standard pattern memory in which a voice pattern of a predetermined voice or sound is stored as a positive reference pattern and also at least one voice or sound pattern generated by said predetermined voice or sound similar to the first-mentioned voice pattern is stored as a negative reference pattern, a pattern comparator for calculating the dissimilarities of an input voice pattern with respect to both the positive reference pattern and the negative reference pattern, and a discriminator for providing a coincidence confirmation output signal when the dissimilarity with respect to the positive reference pattern is less than that with respect to the negative reference pattern.

2. A voice recognition system according to claim 1 wherein said discriminator comprises a minimum value selector for comparing the dissimilarities with one another to produce a minimum value signal and a first signal when the minimum value signal is related to the positive reference pattern, a threshold value circuit for comparing the minimum value signal with a threshold value to produce a second signal when the minimum value is less than the threshold value, and means for generating said coincidence confirmation output signal when the first and second signals are both present.

3. A system for sound recognition comprising:

a first means for storing a first group of information representing a correct sound pattern data;

a second means for storing a second group of information representing at least one incorrect sound pattern data;

means for receiving input sound information;

a first generating means coupled to said first and second means and said receiving means for generating a first signal when said input sound information is detected as said frist group of information, and a second signal when said input sound information is detected as said second group of information;

a second generating means for generating a confirmation signal; and

a third means coupled to said first and second generating means for providing said confirmation signal when said first signal is present and for inhibiting said confirmation signal when said second signal is present.

4. A system for sound recognition as claimed in claim 3, in which said correct sound pattern data represents a password pronounced by a person to be registered, and said incorrect sound pattern data represents a word different from said password, said word being pronounced by said person to be registered.