Patent US4833713A successfully refreshed from Google Patents.
US4833713A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Voice recognition system
Assignee: Ricoh Co Ltd
•
Filing: 1986-09-04
•
Granted: 1989-05-23
•
Expires: 2006-09-04
Abstract
Abstract A voice or sound recognition system including a microphone for converting a voice into an electrical voice signal, a frequency analyzer for generating a voice pattern in the form of a time-frequency distribution, and a matching unit for matching the voice pattern with registered voice patterns. A voice pattern sometimes contains a bass bar section starting from the beginning of the voice pattern over a time period. In one form of the present invention, the bass bar section is detected and/or eliminated before processing the voice pattern for the purpose of registration or matching. The voice level is sometimes too strong or too weak for appropriate processing. In another form of the present invention, a voice recognition system including a voice input cancelling function is provided. In addition, a system for detecting a voice interval for use in voice data processing, including a device for determining a start point of the voice interval is provided.
Inventors
- 👤 Tetsuya Muroi
- 👤 Seigou Yasuda
- 👤 Toshiki Kawamoto
- 👤 Junichiroh Fujimoto
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 23:16
CPC Classifications
G; G10; G10L; G10L15/00
Claims Analysis
Total Claims: 46
Claim 1
Independent Claim
137 words
A system for registering a voice pattern by superposing two or more voice patterns for the same sound a multiple of times, comprising: converting means for converting a sound into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form a time-frequency distribution; detecting means for detecting a section from the beginning of said voice pattern where voice energy of said sound is equal to or less than a first predetermined value and partial voice energy of a low frequency component of said sound is equal to or larger than a second predetermined value; and superposing means for superposing said voice pattern onto a previously created voice pattern for the same sound after completion of said section to form a combined voice pattern.
Claim 2
Independent Claim
137 words
A system for registering a voice pattern by superposing two or more voice patterns for the same sound a multiple of times, comprising: converting means for converting a sound into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form a time-frequency distribution; detecting means for detecting a section from the beginning of said voice pattern where voice energy of said sound is equal to or less than a first predetermined value and partial voice energy of a low frequency component of said sound is equal to or larger than a second predetermined value; and superposing means for superposing said voice pattern onto a previously created voice pattern for the same sound after completion of said section to form a combined voice pattern.
Claim 3
Dependent Claim
17 words
The system of claim 1 wherein said section is a bass bar section of said voice pattern.
Claim 4
Dependent Claim
12 words
The system of claim 1 wherein said converting means includes a microphone.
Claim 5
Dependent Claim
24 words
The system of claim 1 wherein said processing means includes a frequency analyzer provided with a plurality of band-pass filters different in frequency range.
Claim 6
Dependent Claim
41 words
The system of claim 1 wherein said processing means includes a maximum value detector detecting a maximum value of said voice patter and said first predetermined value is set in a first range from 10 to 40% of said maximum value.
Claim 7
Dependent Claim
24 words
The system of claim 5 wherein said second threshold value is set in a second range from 60 to 100% of said maximum value.
Claim 8
Dependent Claim
22 words
The system of claim 6 wherein said low frequency component is set in a third range from 200 Hz to 1 kHz.
Claim 9
Dependent Claim
22 words
The system of claim 7 wherein said first, second and third ranges are set approximately at 20%, 80% and 500 Hz, respectively.
Claim 10
Independent Claim
142 words
A system for registering a voice pattern by superposing two or more voice patterns for the same sound a multiple of times, comprising: converting means for converting a sound into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution. detecting means for detecting a section from the beginning of said voice pattern where voice energy of said sound is equal to or less than a first predetermined value and partial voice energy of a low frequency component of said sound is equal to or larger than a second predetermined value, said detecting means cutting off said section upon detection; and superposing means for superposing said voice pattern onto a previously created voice pattern for the same sound to form a combined voice pattern.
Claim 11
Independent Claim
142 words
A system for registering a voice pattern by superposing two or more voice patterns for the same sound a multiple of times, comprising: converting means for converting a sound into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution. detecting means for detecting a section from the beginning of said voice pattern where voice energy of said sound is equal to or less than a first predetermined value and partial voice energy of a low frequency component of said sound is equal to or larger than a second predetermined value, said detecting means cutting off said section upon detection; and superposing means for superposing said voice pattern onto a previously created voice pattern for the same sound to form a combined voice pattern.
Claim 12
Dependent Claim
17 words
The system of claim 9 wherein said section is a bass bar section of said voice pattern.
Claim 13
Dependent Claim
12 words
The system of claim 9 wherein said converting means includes a microphone.
Claim 14
Dependent Claim
23 words
The system of claim 9 wherein said processing means includes a frequency analyzer provided with plurality of band-pass filters different in frequency range.
Claim 15
Dependent Claim
41 words
The system of claim 9 wherein said processing means includes a maximum value detector detecting a maximum value of said voice pattern and said first predetermined value is set in a first range from 10 to 40% of said maximum value.
Claim 16
Dependent Claim
24 words
The system of claim 13 wherein said second threshold value is set in a second range from 60 to 100% of said maximum value.
Claim 17
Dependent Claim
22 words
The system of claim 14 wherein said low frequency component is set in a third range from 200 Hz to 1 kHz.
Claim 18
Dependent Claim
22 words
The system of claim 15 wherein said first, second and third ranges are set approximately at 20%, 80% and 500 Hz, respectively.
Claim 19
Dependent Claim
113 words
A voice recognizing system, comprising: converting means for converting a voice to be recognized into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution; detecting means for detecting a section from the beginning of said voice pattern where voice energy of said voice is equal to or less than a first predetermined value and partial voice energy of a low frequency component of said voice is equal to or larger than a second predetermined value; and matching means for matching said voice pattern with at least one of a plurality of registered voice patterns.
Claim 20
Dependent Claim
113 words
A voice recognizing system, comprising: converting means for converting a voice to be recognized into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution; detecting means for detecting a section from the beginning of said voice pattern where voice energy of said voice is equal to or less than a first predetermined value and partial voice energy of a low frequency component of said voice is equal to or larger than a second predetermined value; and matching means for matching said voice pattern with at least one of a plurality of registered voice patterns.
Claim 21
Dependent Claim
17 words
The system of claim 17 wherein said section is a bass bar section of said voice pattern.
Claim 22
Dependent Claim
12 words
The system of claim 17 wherein said converting means includes a microphone.
Claim 23
Dependent Claim
24 words
The system of claim 17 wherein said processing means includes a frequency analyzer provided with a plurality of band-pass filters different in frequency range.
Claim 24
Dependent Claim
41 words
The system of claim 17 wherein said processing means includes a maximum value detector detecting a maximum value of said voice pattern and said first predetermined value is set in a first range from 10 to 40% of said maximum value.
Claim 25
Dependent Claim
24 words
The system of claim 21 wherein said second threshold value is set in a second range from 60 to 100% of said maximum value.
Claim 26
Dependent Claim
22 words
The system of claim 22 wherein said low frequency component is set in a third range from 200 Hz to 1 kHz.
Claim 27
Dependent Claim
22 words
The system of claim 23 wherein said first, second and third ranges are set approximately at 20%, 80% and 500 Hz, respectively.
Claim 28
Dependent Claim
150 words
A voice recognizing system, comprising: converting means for converting a voice to be recognized into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution and also a voice power signal, said voice pattern being comprised of a collection of frames in timed sequence; identifying means for identifying said voice pattern by matching with a plurality of registered voice patterns; detecting means for detecting a voice interval by comparing said voice power signal with a first reference value; adding means for adding voice powers of said voice power signal over a predetermined number of frames; and means for comparing said added voice power with a pair of lower and upper reference values and cancelling said voice pattern if said added value is outside a range between said lower and upper reference values.
Claim 29
Dependent Claim
150 words
A voice recognizing system, comprising: converting means for converting a voice to be recognized into an electrical voice signal; processing means for processing said electrical voice signal in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution and also a voice power signal, said voice pattern being comprised of a collection of frames in timed sequence; identifying means for identifying said voice pattern by matching with a plurality of registered voice patterns; detecting means for detecting a voice interval by comparing said voice power signal with a first reference value; adding means for adding voice powers of said voice power signal over a predetermined number of frames; and means for comparing said added voice power with a pair of lower and upper reference values and cancelling said voice pattern if said added value is outside a range between said lower and upper reference values.
Claim 30
Dependent Claim
33 words
The system of claim 25 wherein the voice powers of said predetermined number of frames are added as long as their voice powers are equal to or higher than a second reference value.
Claim 31
Dependent Claim
31 words
The system of claim 26 wherein said second reference value and said lower and upper reference values are varied in a predetermined manner as a function of a background noise level.
Claim 32
Dependent Claim
60 words
The system of claim 25 wherein said adding means adds voice powers of said voice power signal over the entire voice interval and divides an added voice power with the total number of frames to define an average frame power, and wherein said means for comparing compares said average frame power with said pair of lower and upper reference values.
Claim 33
Independent Claim
149 words
A system for detecting a voice interval for use in voice registration or recognition, comprising: converting means for converting a voice into an electrical voice signal; processing means for processing said electrical voice signal at a predetermined time interval in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution frame by frame, said processing means generating a voice power of said voice pattern, a first partial voice power of a low frequency range of said voice pattern and a second partial voice power of said voice pattern; and comparing means for comparing said first partial voice power with a predetermined threshold value and also with said second partial voice power and determining a start point of said voice interval if said first partial voice power is found to be larger than both of said predetermined threshold value and said second partial voice power.
Claim 34
Independent Claim
149 words
A system for detecting a voice interval for use in voice registration or recognition, comprising: converting means for converting a voice into an electrical voice signal; processing means for processing said electrical voice signal at a predetermined time interval in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution frame by frame, said processing means generating a voice power of said voice pattern, a first partial voice power of a low frequency range of said voice pattern and a second partial voice power of said voice pattern; and comparing means for comparing said first partial voice power with a predetermined threshold value and also with said second partial voice power and determining a start point of said voice interval if said first partial voice power is found to be larger than both of said predetermined threshold value and said second partial voice power.
Claim 35
Dependent Claim
12 words
The system of claim 29 wherein said converting means includes a microphone.
Claim 36
Dependent Claim
63 words
The system of claim 29 wherein said processing means includes a plurality of band-pass filters different in frequency range and wherein said said low frequency range is defined by a predetermined number of said band-pass filters at a low frequency end thereof and said high frequency range is defined by a predetermined number of said band-pass filters at a high frequency end thereof.
Claim 37
Dependent Claim
32 words
The system of claim 29 wherein said processing means also generates a third partial voice power of an intermediate frequency range between said low and high frequency ranges of said voice pattern.
Claim 38
Dependent Claim
90 words
The system of claim 29 further comprising calculating means for calculating a difference power spectrum for each frame and determining a start point of said voice interval when said difference power spectrum is found to be larger than a predetermined value and an OR gate having a first input terminal for receiving an output signal from said comparing means, a second input terminal for receiving an output signal from said calculating means and an output terminal for supplying a start point pulse indicating the start point of said voice interval.
Claim 39
Independent Claim
149 words
A system for detecting a voice interval for use in voice registration or recognition, comprising: converting means for converting a voice into an electrical voice signal; processing means for processing said electrical voice signal at a predetermined time interval in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution frame by frame, said processing means generating a voice power of said voice pattern, a first partial voice power of a low frequency range of said voice pattern and a second partial voice power of said voice pattern; and comparing mean for comparing said second partial voice power with a predetermined threshold value and also with said first partial voice power and determining a start point of said voice interval if said second partial voice power is found to be larger than both of said predetermined threshold value and said second partial voice power.
Claim 40
Independent Claim
149 words
A system for detecting a voice interval for use in voice registration or recognition, comprising: converting means for converting a voice into an electrical voice signal; processing means for processing said electrical voice signal at a predetermined time interval in a predetermined manner to produce a voice pattern in the form of a time-frequency distribution frame by frame, said processing means generating a voice power of said voice pattern, a first partial voice power of a low frequency range of said voice pattern and a second partial voice power of said voice pattern; and comparing mean for comparing said second partial voice power with a predetermined threshold value and also with said first partial voice power and determining a start point of said voice interval if said second partial voice power is found to be larger than both of said predetermined threshold value and said second partial voice power.
Claim 41
Dependent Claim
12 words
The system of claim 34 wherein said converting means includes a microphone.
Claim 42
Dependent Claim
63 words
The system of claim 34 wherein said processing means includes a plurality of band-pass filters different in frequency range and wherein said said low frequency range is defined by a predetermined number of said band-pass filters at a low frequency end thereof and said high frequency range is defined by a predetermined number of said band-pass filters at a high frequency end thereof.
Claim 43
Dependent Claim
32 words
The system of claim 34 wherein said processing means also generates a third partial voice power of an intermediate frequency range between said low and high frequency ranges of said voice pattern.
Claim 44
Dependent Claim
44 words
The system of claim 37 further comprising inhibiting means for inhibiting said start point signal when said comparing means finds that said second partial voice power is larger than said first and third partial voice powers, but is smaller than a predetermined threshold value.
Claim 45
Dependent Claim
47 words
The system of claim 38 wherein said inhibiting means includes an AND gate having a first input terminal for receiving an inhibit signal from said comparing means, a second input terminal for receiving said start point signal, and an output terminal for supplying a start point pulse.
Claim 46
Dependent Claim
90 words
The system of claim 34 further comprising calculating means for calculating a difference power spectrum for each frame and determining a start point of said voice interval when said difference power spectrum is found to be larger than a predetermined value and an OR gate having a first input terminal for receiving an output signal from said comparing means, a second input terminal for receiving an output signal from said calculating means and an output terminal for supplying a start point pulse indicating the start point of said voice interval.
References Cited (Backward Citations)
US4144582A
Cited
US4087630A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1992-05-22 | 1992-11-21 | 1993-05-23 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1996-05-22 | 1996-11-21 | 1997-05-23 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2000-05-22 | 2000-11-21 | 2001-05-23 | $7700.00 | Window Closed / Lapsed |