US4962535A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Voice recognition system
Assignee: Fujitsu Ltd
•
Filing: 1990-01-12
•
Granted: 1990-10-09
•
Expires: 2010-01-12
Abstract
Abstract A voice recognition system for selecting word templates necessary for voice recognition from among a plurality of word templates. The system includes an input phoneme extraction unit for extracting distinctive phonemes which can be clearly recognized from an input pattern of the voice, and all phonemes possibly existing in the input pattern, and a dictionary phoneme extraction unit for extracting the distinctive phonemes which can be clearly recognized and can be previously determined at each word template, and all phonemes possibly existing at each word template. A pre-selector selects valid word templates for performing voice recognition based on phoneme information extracted by the input phoneme extraction unit and the dictionary phoneme extraction unit.
Inventors
- 👤 Shinta Kimura
- 👤 Toru Sanada
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 07:43
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/08; G10L15/10; G10L15/28; G10L15/02; G10L2015/025; G10L15/22; G10L2015/226; G10L2015/228
Claims Analysis
Total Claims: 4
Claim 1
Independent Claim
319 words
A voice recognition system for selecting word templates necessary for voice recognition from among a plurality of word templates, comprising: an input phoneme extraction unit for extracting distinctive phonemes which can be clearly recognized from an input pattern of a voice and for extracting all phonemes possibly existing in the input pattern, said input phoneme extraction unit generates first bit expression values of the distinctive phonemes which can be clearly recognized from the input pattern, and generates second bit expression values of all phonemes possibly existing in the input pattern; a dictionary phoneme extraction unit for extracting the distinctive phonemes which are clearly recognized and can be previously determined at each word template and for extracting all phonemes possibly existing at each word template, said dictionary phoneme extraction unit generates third bit expression values of the distinctive phonemes which can be clearly recognized and can be previously determined at each word template, and generates fourth bit expression values of all phonemes possibly existing in each word template; a pre-selector, coupled between said input phoneme extracting unit and said dictionary phoneme extracting unit, for selecting valid word templates for performing voice recognition based on phoneme information extracted by said input phoneme extraction unit and said dictionary phoneme extraction unit, said preselector selects valid word templates by employing the following formula: (D.sub.i ·I')⊕I'·(D.sub.i ·I)⊕D.sub.i ' wherein D i is the fourth bit expression value, D i ' is the third bit expression value, I is the second bit expression value, I' is the first bit expression value, i is the number of the word template, and ⊕ denotes an exclusive OR operation, said preselector also determining whether or not all bits of the above formula indicate the value "1"; and a bit expression memory, coupled between said dictionary phoneme extraction unit and said pre-selector, for storing the third and fourth bit expression values previously calculated by said dictionary phoneme extraction unit.
Claim 2
Dependent Claim
319 words
A voice recognition system for selecting word templates necessary for voice recognition from among a plurality of word templates, comprising: an input phoneme extraction unit for extracting distinctive phonemes which can be clearly recognized from an input pattern of a voice and for extracting all phonemes possibly existing in the input pattern, said input phoneme extraction unit generates first bit expression values of the distinctive phonemes which can be clearly recognized from the input pattern, and generates second bit expression values of all phonemes possibly existing in the input pattern; a dictionary phoneme extraction unit for extracting the distinctive phonemes which are clearly recognized and can be previously determined at each word template and for extracting all phonemes possibly existing at each word template, said dictionary phoneme extraction unit generates third bit expression values of the distinctive phonemes which can be clearly recognized and can be previously determined at each word template, and generates fourth bit expression values of all phonemes possibly existing in each word template; a pre-selector, coupled between said input phoneme extracting unit and said dictionary phoneme extracting unit, for selecting valid word templates for performing voice recognition based on phoneme information extracted by said input phoneme extraction unit and said dictionary phoneme extraction unit, said preselector selects valid word templates by employing the following formula: (D.sub.i ·I')⊕I'·(D.sub.i ·I)⊕D.sub.i ' wherein D i is the fourth bit expression value, D i ' is the third bit expression value, I is the second bit expression value, I' is the first bit expression value, i is the number of the word template, and ⊕ denotes an exclusive OR operation, said preselector also determining whether or not all bits of the above formula indicate the value "1"; and a bit expression memory, coupled between said dictionary phoneme extraction unit and said pre-selector, for storing the third and fourth bit expression values previously calculated by said dictionary phoneme extraction unit.
Claim 3
Dependent Claim
78 words
A voice recognition system as claimed in claim 1, wherein said pre-selector comprises: dictionary data buffer means for receiving phonemes from said dictionary phoneme extraction unit and for temporarily storing the phonemes; connection circuit means for receiving the first through fourth bit expression values; and selection calculation circuit means, connected between said dictionary data buffer means and said connection circuit, for receiving outputs from said connection circuit means and outputting resultant data to said dictionary data buffer means.
Claim 4
Dependent Claim
136 words
A voice recognition system as claimed in claim 2, wherein said selection calculation circuit means comprises: first and second NOT circuits, operatively connected to receive said second and fourth bit expression values, respectively, and outputting respective signals; first and second OR circuits, operatively connected to said first and second NOT circuits, and operatively connected to receive said first and third bit expression values, respectively, and said outputs from said first and second NOT circuits, respectively, for outputting respective signals; an AND circuit, operatively connected to said first and second OR circuits, for receiving the output signals from said first and second OR circuits and outputting a signal; and comparator means, operatively connected to said AND circuits and operatively connected to receive a "-1" data, for determining whether all bits output from said AND circuit are "1".
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1993-10-08 | 1994-04-09 | 1994-10-09 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1997-10-08 | 1998-04-09 | 1998-10-09 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2001-10-08 | 2002-04-09 | 2002-10-09 | $7700.00 | Window Closed / Lapsed |