Patent US4559604A successfully refreshed from Google Patents.
US4559604A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Pattern recognition method
Assignee: Hitachi Ltd
•
Filing: 1981-09-21
•
Granted: 1985-12-17
•
Expires: 2001-09-21
Abstract
Abstract In a machine implemented voice recognition method, as a first step speech signals are analyzed for feature vectors which are used to compare input signals with prestored reference signals. Patterns of any suitable form are used to calculate a similarity distance measure d IJ which is tested against a threshold to select likely candidates as a first step. A second step selects the most likely candidate by using "common nature" parameters of phonemes such as relative occurrence. Five embodiments of the second step are disclosed, each using a "common nature" criteria of inference to infer (select) the most likely candidate: (1) d' I =W 1 ,.W 2 .W 3 where W is a weighting factor; (2) d" I =C I d' I where C I is a correction factor; (3) max p(i,j) where p(i) is the probability of occurrence of the i th phoneme; (4) min d' ij as a variation of max p(i,j); and (5) N(i) is the numerical similarity of the common characteristics of the selected candidates.
Inventors
- 👤 Akira Ichikawa
- 👤 Hiroko Matsuzaka
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 21:50
CPC Classifications
G; G10; G10L; G10L15/00; G06; G06F; G06F18/00; G06F18/20; G06F18/25; G06F18/254
Claims Analysis
Total Claims: 20
Claim 1
Independent Claim
79 words
A machine implemented pattern recognition method comprising comparing input patterns with standard patterns, selecting a plurality of candidates that are likely to be input patterns according to identified values that represent the results of the comparison, and inferring an input pattern among the selected candidates that are likely to be input patterns according to a predetermined criterion of inference which is determined from the commonness of the nature of each of the selected candidates with the other selected candidates.
Claim 2
Dependent Claim
79 words
A machine implemented pattern recognition method comprising comparing input patterns with standard patterns, selecting a plurality of candidates that are likely to be input patterns according to identified values that represent the results of the comparison, and inferring an input pattern among the selected candidates that are likely to be input patterns according to a predetermined criterion of inference which is determined from the commonness of the nature of each of the selected candidates with the other selected candidates.
Claim 3
Dependent Claim
56 words
A machine implemented pattern recognition method according to claim 1, wherein said criteron of inference is a number of candidates having a nature common to that of said selected candidates, and a candidate having the greatest number of said candidates having a nature common to that of said selected candidate is inferred as the input pattern.
Claim 4
Dependent Claim
77 words
A pattern recognition method according to claim 1, wherein said criterion of inference is a product of a value which corresponds to an inverse number of the candidates having a nature common to that of said selected candidates, a value corresponding to said identified value of each of the candidates, and an average value of said identified value in each of the candidates and in the candidates having a nature common to said each of the candidates.
Claim 5
Dependent Claim
43 words
A pattern recognition method according to claim 1, wherein said criterion of inference is a value corresponding to a weighed average value of a similarity degree and an identified value between said selected candidates and candidates having a nature common to said candidates.
Claim 6
Dependent Claim
117 words
A pattern recognition method according to claim 1, wherein said criterion of inference assumes a quantity given by ##EQU18## where p(i) denotes an appearing probability of the input pattern i (i=1, 2, . . . N), p(d i ,j |i,j) denotes a probability in which a quantity corresponding to the similarity degree between the input pattern i and the standard pattern j (j=1, 2, . . . N) is d i ,j, p (i|d i ,j) denotes a probability in which the input pattern is i when the quantity corresponding to said similarity degree is d i ,j, and p (i,j) denotes a probability in which an input pattern i is checked with a standard pattern j.
Claim 7
Dependent Claim
130 words
A machine implemented pattern recognition method for inferring an input pattern comprising the steps: comparing an input pattern with a plurality of standard patterns; selecting a plurality of candidates that are likely to be the input pattern based upon identified values that represent the results of the comparison of the input pattern with the standard patterns; and inferring an input pattern from the plurality of candidates based upon a predetermined criterion of inference for evaluating the selected plurality of candidates, the predetermined criterion of inference being different than the criteria for selecting the plurality of candidates, and utilizing at least one characteristic parameter of each of the selected plurality of candidates and the commonness of at least one characteristic parameter within each selected candidate and the other remaining selected candidates.
Claim 8
Dependent Claim
130 words
A machine implemented pattern recognition method for inferring an input pattern comprising the steps: comparing an input pattern with a plurality of standard patterns; selecting a plurality of candidates that are likely to be the input pattern based upon identified values that represent the results of the comparison of the input pattern with the standard patterns; and inferring an input pattern from the plurality of candidates based upon a predetermined criterion of inference for evaluating the selected plurality of candidates, the predetermined criterion of inference being different than the criteria for selecting the plurality of candidates, and utilizing at least one characteristic parameter of each of the selected plurality of candidates and the commonness of at least one characteristic parameter within each selected candidate and the other remaining selected candidates.
Claim 9
Dependent Claim
54 words
A machine implemented pattern recognition method in accordance with claim 6, wherein said criterion of inference is determined for each of said selected candidates by calculating the number of candidates having a characteristic parameter common to each selected candidate and the input pattern is inferred by chosing the candidate having the greatest calculated number.
Claim 10
Dependent Claim
81 words
A machine implemented pattern recognition method according to claim 6, wherein said criterion of inference is a product of a value which corresponds to an inverse number of the candidates having a characteristic parameter common to that of said selected candidates, a value corresponding to said identified value of each of the candidates, and an average value of said identified value in each of the candidates and in the candidates having a characteristic parameter common to said each of the candidates.
Claim 11
Dependent Claim
46 words
A machine implemented pattern recognition method according to claim 6, wherein said criterion of inference is a value corresponding to a weighed average value of a similarity degree and an identified value between said selected candidates and candidates having a characteristic parameter common to said candidates.
Claim 12
Dependent Claim
119 words
A machine implemented pattern recognition method according to claim 6, wherein said criterion of inference assumes a quantity given by ##EQU19## where p(i) denotes an appearing probability of the input pattern i (i=1, 2, . . . N), p(d i ,j |i,j) denotes a probability in which a quantity corresponding to the similarity degree between the input pattern i and the standard pattern j (j=1, 2, . . . N) is d i ,j, p (i|d i ,j) denotes a probability in which the input pattern is i when the quantity corresponding to said similarity degree is d i ,j, and p (i,j) denotes a probability in which an input pattern i is checked with a standard pattern j.
Claim 13
Dependent Claim
105 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criterion of inference relying upon the common nature of the selected candidates with other candidates, wherein said criterion of inference is determined for each of said selected candidates by calculating the number of candidates having a characteristic parameter common to each selected candidate and the input pattern is inferred by choosing the candidate having the greatest calculated number.
Claim 14
Dependent Claim
105 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criterion of inference relying upon the common nature of the selected candidates with other candidates, wherein said criterion of inference is determined for each of said selected candidates by calculating the number of candidates having a characteristic parameter common to each selected candidate and the input pattern is inferred by choosing the candidate having the greatest calculated number.
Claim 15
Dependent Claim
133 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criteron of inference relying upon the common nature of the selected candidates with other candidates, wherein said criteron of inference is a product of a value which corresponds to an inverse number of the candidates having a characteristic parameter common to that of said selected candidates, a value corresponding to said identified value of each of the candidates, and an average value of said identified value in each of the candidates and in the candidates having a characteristic parameter common to said each of the candidates.
Claim 16
Dependent Claim
133 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criteron of inference relying upon the common nature of the selected candidates with other candidates, wherein said criteron of inference is a product of a value which corresponds to an inverse number of the candidates having a characteristic parameter common to that of said selected candidates, a value corresponding to said identified value of each of the candidates, and an average value of said identified value in each of the candidates and in the candidates having a characteristic parameter common to said each of the candidates.
Claim 17
Dependent Claim
98 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criterion of inference relying upon the common nature of the selected candidates with other candidates, wherein said criterion of inference is a value corresponding to a weighed average value of a similarity degree and an identified value between said selected candidates and candidates having a characteristic parameter common to said candidates.
Claim 18
Dependent Claim
98 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criterion of inference relying upon the common nature of the selected candidates with other candidates, wherein said criterion of inference is a value corresponding to a weighed average value of a similarity degree and an identified value between said selected candidates and candidates having a characteristic parameter common to said candidates.
Claim 19
Dependent Claim
171 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criterion of inference relying upon the common nature of the selected candidates with other candidates, wherein said criterion of inference assumes a quantity given by ##EQU20## where p(i) denotes an appearing probability of the input pattern i (i=1, 2, . . . N), p(d i ,j /i,j) denotes a probability in which a quantity corresponding to the similarity degree between the input pattern i and the standard pattern j (j=1, 2, . . . N) is d i ,j, p (i/d i ,j) denotes a probability in which the input pattern is i when the quantity corresponding to said similarity degree is d i ,j, and p (i,j) denotes a probability in which an input pattern i is checked with a standard pattern j.
Claim 20
Dependent Claim
171 words
A voice pattern machine implemented method comprising: a first step of comparing an unknown input pattern with prestored standard voice patterns using a distance measure to find probable candidates and a second step of inferring the unknown pattern from the plurality of candidates based on a predetermined criterion of inference relying upon the common nature of the selected candidates with other candidates, wherein said criterion of inference assumes a quantity given by ##EQU20## where p(i) denotes an appearing probability of the input pattern i (i=1, 2, . . . N), p(d i ,j /i,j) denotes a probability in which a quantity corresponding to the similarity degree between the input pattern i and the standard pattern j (j=1, 2, . . . N) is d i ,j, p (i/d i ,j) denotes a probability in which the input pattern is i when the quantity corresponding to said similarity degree is d i ,j, and p (i,j) denotes a probability in which an input pattern i is checked with a standard pattern j.
References Cited (Backward Citations)
US3265814A
Cited
US3643215A
Cited
US3679830A
Cited
US3946157A
Cited
US4027284A
Cited
US4100370A
Cited
US4286115A
Cited
US4292471A
Cited
US4394538A
Cited
US4400828A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1988-12-16 | 1989-06-17 | 1989-12-17 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1992-12-16 | 1993-06-17 | 1993-12-17 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1996-12-16 | 1997-06-17 | 1997-12-17 | $7700.00 | Window Closed / Lapsed |