US4751737A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Template generation method in a speech recognition system
Assignee: Motorola Solutions Inc
•
Filing: 1985-11-06
•
Granted: 1988-06-14
•
Expires: 2005-11-06
Abstract
Abstract Disclosed is a method for generating word templates for a speech recognition system. It is used where speech is represented by data in frames of equal time intervals. The method includes generating an interim template, generating a time alignment path between the interim template and a token, mapping frames from the interim template and the token along the time alignment path onto an averaged time axis, and combining data associated with the mapped frames to produce composite frames representative of the final word template. The method realizes advantages of reduced memory usage and a realistic data average from each contributing averaged word.
Inventors
- 👤 Ira A. Gerson
- 👤 Brett L. Lindsley
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 08:37
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/06; G10L15/063
Claims Analysis
Total Claims: 33
Claim 1
Independent Claim
99 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, a method for generating a final word template from a plurality of tokens, comprising the steps of: (a) forming an interim template representative of at least one token; (b) generating a time alignment path between said interim template and an additional token; (c) mapping frames from said interim template and said additional token along said time alignment path onto an averaged time axis; and (d) combining data associated with said mapped frames to produce composite frames representative of the final word template.
Claim 2
Dependent Claim
99 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, a method for generating a final word template from a plurality of tokens, comprising the steps of: (a) forming an interim template representative of at least one token; (b) generating a time alignment path between said interim template and an additional token; (c) mapping frames from said interim template and said additional token along said time alignment path onto an averaged time axis; and (d) combining data associated with said mapped frames to produce composite frames representative of the final word template.
Claim 3
Dependent Claim
67 words
A method for generating a final word template, according to claim 1, wherein forming said interim template includes the steps of: generating a time alignment path between a first and second token; mapping frames from said first and second token along said time alignment path onto an averaged time axis; and combining data associated with said mapped frames to produce composite frames representative of the interim template.
Claim 4
Dependent Claim
36 words
A method for generating a final word template, according to claim 1, wherein combining data comprises averaging the data such that the resultant data is approximately equally contributed to by each token the final template represents.
Claim 5
Dependent Claim
42 words
A method for generating a final word template, according to claim 1, including the steps of comparing the data between the interim template and the additional token to produce a distance measure, and comparing said distance measure to a predetermined distance measure.
Claim 6
Dependent Claim
23 words
A method for generating a final word template, according to claim 1, including the step of weighting the data representing said interim template.
Claim 7
Dependent Claim
27 words
A method for generating a final word template, according to claim 1, including the step of repetitively averaging data representing tokens with data representing said interim template.
Claim 8
Dependent Claim
33 words
A method for generating a final word template, according to claim 1, including the step of accumulating values assigned to the direction taken along said time alignment path to produce said composite frames.
Claim 9
Dependent Claim
33 words
A method for generating a final word template, according to claim 1, wherein said combining includes the step of accumulating the data representing said interim template and the data representing said additional token.
Claim 10
Dependent Claim
27 words
A method for generating a final word template, according to claim 1, including the step of normalizing a sum of accumulated data to produce said composite frames.
Claim 11
Dependent Claim
112 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, a method for generating a final word template from a plurality of tokens, comprising the steps of: (a) forming an interim template representative of at least one token; (b) generating a time alignment path between said interim template and an additional token; (c) weighting the data representing said interim template proportional to the number of tokens said interim template represents; and (d) combining frames from said interim template with frames from said additional token, dependent upon the number of tokens which the interim template represents, to produce output frames representative of the final word template.
Claim 12
Dependent Claim
112 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, a method for generating a final word template from a plurality of tokens, comprising the steps of: (a) forming an interim template representative of at least one token; (b) generating a time alignment path between said interim template and an additional token; (c) weighting the data representing said interim template proportional to the number of tokens said interim template represents; and (d) combining frames from said interim template with frames from said additional token, dependent upon the number of tokens which the interim template represents, to produce output frames representative of the final word template.
Claim 13
Dependent Claim
35 words
A method for generating a final word template, according to claim 10, including the step of mapping frames from said interim template and said token along said time alignment path onto an averaged time axis.
Claim 14
Dependent Claim
67 words
A method for generating a final word template, according to claim 10, wherein forming said interim template includes the steps of generating a time alignment path between a first and second token; mapping frames from said first and second token along said time alignment path onto an averaged time axis; and combining data associated with said mapped frames to produce composite frames representative of the interim template.
Claim 15
Dependent Claim
42 words
A method for generating a final word template, according to claim 10, including the steps of comparing the data between the interim template and the additional token to produce a distance measure and comparing said distance measure to a predetermined distance measure.
Claim 16
Dependent Claim
30 words
A method for generating a final word template, according to claim 10, wherein said interim template includes an approximately equal contribution of data from each token said interim template represents.
Claim 17
Dependent Claim
38 words
A method for generating a final word template according to claim 10, wherein weighting the data representing said interim template includes the step of assigning at least one value to each direction taken along said time alignment path.
Claim 18
Dependent Claim
34 words
A method for generating a final word template, according to claim 10, wherein said combining includes the step of accumulating the weighted data representing said interim template and the data representing said additional token.
Claim 19
Dependent Claim
25 words
A method for generating a final word template, according to claim 10, including the step of normalizing a sum of accumulated data representing averaged frames.
Claim 20
Dependent Claim
104 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, an arrangement for generating a final word template from a plurality of tokens, including: (a) means for forming an interim template representative of at least one token; (b) means for generating a time alignment path between said interim template and an additional token; (c) means for mapping frames from said interim template and said additional token along said time alignment path onto an averaged time axis; and (d) means for combining data associated with said mapped frames to produce composite frames representative of a final word template.
Claim 21
Dependent Claim
104 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, an arrangement for generating a final word template from a plurality of tokens, including: (a) means for forming an interim template representative of at least one token; (b) means for generating a time alignment path between said interim template and an additional token; (c) means for mapping frames from said interim template and said additional token along said time alignment path onto an averaged time axis; and (d) means for combining data associated with said mapped frames to produce composite frames representative of a final word template.
Claim 22
Dependent Claim
21 words
An arrangement, according to claim 18, further comprising means for normalizing an accumulation of combined data to form said composite frames.
Claim 23
Dependent Claim
37 words
An arrangement, according to claim 18, including means for comparing the data between the interim template and the additional token to produce a distance measure, and means for comparing said distance measure to a predetermined distance measure.
Claim 24
Dependent Claim
24 words
An arrangement, according to claim 18, wherein said interim template includes an approximately equal contribution of data from each token said interim template represents.
Claim 25
Dependent Claim
16 words
An arrangement, according to claim 18, including means for weighting the data representing said interim template.
Claim 26
Dependent Claim
20 words
An arrangement, according to claim 18, including means for repetitively averaging data representing tokens with data representing said interim template.
Claim 27
Dependent Claim
117 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, an arrangement for generating a final word template from a plurality of tokens, including: (a) means for forming an interim template representative of at least one token; (b) means for generating a time alignment path between said interim template and an additional token; (c) means for weighting the data representing said interim template proportional to the number of tokens said interim template represents; and (d) means for combining frames from said interim template with frames from said additional token, dependent upon the number of tokens which the interim template represents, to produce output frames representative of the final word template.
Claim 28
Dependent Claim
117 words
In a speech recognition system, wherein speech is represented by data in frames of equal time intervals, an arrangement for generating a final word template from a plurality of tokens, including: (a) means for forming an interim template representative of at least one token; (b) means for generating a time alignment path between said interim template and an additional token; (c) means for weighting the data representing said interim template proportional to the number of tokens said interim template represents; and (d) means for combining frames from said interim template with frames from said additional token, dependent upon the number of tokens which the interim template represents, to produce output frames representative of the final word template.
Claim 29
Dependent Claim
21 words
An arrangement, according to claim 24, further comprising means for normalizing an accumulation of combined data to form said composite frames.
Claim 30
Dependent Claim
37 words
An arrangement, according to claim 24, including means for comparing the data between the interim template and the additional token to produce a distance measure and means for comparing said distance measure to a predetermined distance measure.
Claim 31
Dependent Claim
24 words
An arrangement, according to claim 24, wherein said interim template includes an approximately equal contribution of data from each token said interim template represents.
Claim 32
Dependent Claim
29 words
An arrangement, according to claim 24, including means for mapping frames from said interim template and said additional token along said time alignment path onto an averaged time axis.
Claim 33
Dependent Claim
20 words
An arrangement, according to claim 24, including means for repetitively averaging data representing tokens with data representing said interim template.
References Cited (Backward Citations)
US3582559A
Cited
US4181821A
Cited
US4349700A
Cited
US4348550A
Cited
US4528688A
Cited
US4467437A
Cited
US4363102A
Cited
US4454586A
Cited
US4570232A
Cited
US4596031A
Cited
US4571697A
Cited
US4488243A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1991-06-14 | 1991-12-14 | 1992-06-14 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1995-06-14 | 1995-12-14 | 1996-06-14 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1999-06-14 | 1999-12-14 | 2000-06-14 | $7700.00 | Window Closed / Lapsed |