US4718096A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Speech recognition system
Assignee: SPEECH SYSTEMS Inc
•
Filing: 1986-11-05
•
Granted: 1988-01-05
•
Expires: 2006-11-05
Abstract
Abstract A plurality of microphones are disposed on a body to detect the speech of a speaker. First, second and third microphones may respectively detect the sounds emanating from the speaker's mouth, nose and throat and produce signals representing such sounds. A fourth microphone may detect the fricative and plosive sounds emanating from the speaker's mouth and produce signals representing such sounds. The signals from the different microphones are compared to allow the discrimination of certain speech sounds. For example, a high amplitude of the signal from the nose microphone relative to that from the mouth microphone indicates that a nasal sound such as m, n, or ng was spoken. Identifying signals are provided to the speech recognition system to aid in identifying the speech sounds at each instance. The identifying signals can also select a microphone whose signal can be passed on to the recognition system in its entirety. Signals may also be provided to identify that spoken words such as "paragraph" or "comma" are actually directions controlling the form, rather than the content, of the speech by the speaker. The selected signals, the identifying or classifying signals and the signals representing directions may be recovered by the system of this invention. The selected and identifying signals may be processed to detect syllables of speech and the syllables may be classified into phrases or sentences. The result may then be converted to a printed form representing the speech or utilized in the operation of another device.
Inventors
- 👤 William S. Meisel
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 07:39
CPC Classifications
H; H04; H04R; H04R1/00; H04R1/08; G; G10; G10L; G10L15/00; G10L15/02; G10L21/00; G10L21/02; G10L21/0208; G10L21/0216; G10L2021/02161; G10L2021/02166; H04R2201/00; H04R2201/40; H04R2201/403
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
98 words
In combination in a speech recognition system for processing the speech of a speaker, first means for detecting acoustic sounds substantially emanating from the mouth of the speaker and for producing signals representing such sounds, second means for detecting acoustic sounds substantially emanating from the nose of the speaker and for producing signals representing such sounds, identification means responsive to the signals produced by the first and second detecting means for dynamically identifying the signal from a particular one of the first and second detecting means having at least one predetermined dominant characteristic relative to the other signal.
Claim 2
Dependent Claim
98 words
In combination in a speech recognition system for processing the speech of a speaker, first means for detecting acoustic sounds substantially emanating from the mouth of the speaker and for producing signals representing such sounds, second means for detecting acoustic sounds substantially emanating from the nose of the speaker and for producing signals representing such sounds, identification means responsive to the signals produced by the first and second detecting means for dynamically identifying the signal from a particular one of the first and second detecting means having at least one predetermined dominant characteristic relative to the other signal.
Claim 3
Dependent Claim
65 words
The combination set forth in claim 1 wherein the identifying means is for identifying the signal from a particular one of the first and second detecting means only after the integrated amplitude of such signal becomes dominant relative to the integrated amplitude of the signal from the other one of the first and second detecting means continuously for at least a predetermined period of time.
Claim 4
Independent Claim
49 words
A method of processing the speech of a speaker, including the following steps: detecting acoustic sounds emanating from the mouth and the nose of the speaker, and processing the detected sounds to dynamically identify the detected sound having at least one predetermined dominant characteristic relative to the other sound.
Claim 5
Independent Claim
49 words
A method of processing the speech of a speaker, including the following steps: detecting acoustic sounds emanating from the mouth and the nose of the speaker, and processing the detected sounds to dynamically identify the detected sound having at least one predetermined dominant characteristic relative to the other sound.
Claim 6
Dependent Claim
46 words
A method as set forth in claim 3, including the following steps: operating upon the recovered signals to detect syllables of the speech, classifying the recovered signals to detect words and phrases, and operating upon the classified signals to process the information represented by the speech.
Claim 7
Dependent Claim
38 words
A method as set forth in claim 3, including the following steps: delaying the selection of the detection sound for a predetermined period of time to insure that the detected sound being identified has the predetermined dominant characteristic.
Claim 8
Dependent Claim
70 words
A microphone assembly comprising: a housing having first and second ends; a first microphone disposed adjacent said first end for detecting acoustic sounds substantially emanating from a corner of a speaker's mouth; and second and third microphones disposed adjacent said first end, spaced apart from said first microphone and on opposite sides thereof, one of said second and third microphones for detecting acoustic sounds substantially emanating from the speaker's nose.
Claim 9
Dependent Claim
70 words
A microphone assembly comprising: a housing having first and second ends; a first microphone disposed adjacent said first end for detecting acoustic sounds substantially emanating from a corner of a speaker's mouth; and second and third microphones disposed adjacent said first end, spaced apart from said first microphone and on opposite sides thereof, one of said second and third microphones for detecting acoustic sounds substantially emanating from the speaker's nose.
Claim 10
Dependent Claim
35 words
The microphone assembly defined by claim 6 further comprising first switch means for generating a signal indicating that speech emanating from the speaker's mouth is to be processed as speech by a voice recognition system.
Claim 11
Dependent Claim
36 words
The microphone assembly defined by claim 7 further comprising second switch means for generating a signal indicating that speech emanating from the speaker's mouth is to be processed as instructions input to a voice recognition system.
Claim 12
Dependent Claim
25 words
The microphone assembly defined by claim 7 wherein said first switch means comprises a first button switch disposed adjacent said second end of said housing.
Claim 13
Dependent Claim
25 words
The microphone assembly defined by claim 9 wherein said second switch means comprises a second button switch disposed adjacent said second end of said housing.
Claim 14
Dependent Claim
32 words
The microphone assembly defined by claim 10 wherein said first and second button switches comprise a button switch having first and second detent positions disposed adjacent said second end of said housing.
Claim 15
Dependent Claim
41 words
The microphone assembly defined by claim 11 including a second button switch having first and second detent positions disposed adjacent said second end of said housing on a side thereof opposite said first button switch having first and second detent positions.
Claim 16
Dependent Claim
29 words
The microphone assembly defined by claim 6 further comprising switch means for generating a signal for selecting which of said second and third microphones is to be made active.
Claim 17
Dependent Claim
55 words
The microphone assembly defined by claim 13 wherein said switch means comprises first and second button switches disposed adjacent said second end of said housing on opposite sides thereof wherein one of said button switches is depressed depending upon whether the microphone assembly is held in the speaker's right hand or the speaker's left hand.
Claim 18
Dependent Claim
115 words
The microphone assembly defined by claim 14 wherein said first and second button switches each have first and second detent positions wherein said first detent position is for generating a signal indicating that speech emanating from the speaker's mouth is to be processed as speech by a voice recognition system and said second detent position is for generating a signal indicating that speech emanating from the speaker's mouth is to be processed as instructions input to said voice recognition system, said signal for selecting which of said second and third microphones is to be made active being generated when said switch is depressed to either of said first detent position and said second detent position.
Claim 19
Dependent Claim
30 words
The combination defined by claim 1 further comprising means for providing a distinction between speech to be processed as text and speech to be processed as directives of the speaker.
Claim 20
Dependent Claim
67 words
The combination defined by claim 1 further comprising: (a) filter means for generating signals representing first formant frequencies and second formant frequencies of the signals generated by the first detecting means and the second detecting means; and (b) tone detection means for generating logic signals which indicate characteristics of the speech sounds detected by the first and second means, said characteristics including nasality, partial closure and plosive.
Claim 21
Dependent Claim
34 words
The combination defined by claim 1 further comprising means for producing in a single channel for subsequent processing the signals produced by the first detecting means, the second detecting means and the identification means.
Claim 22
Dependent Claim
73 words
The combination defined by claim 17 further comprising: (a) data buffer means coupled to said filter means and said tone detection means for buffering the data generated by said filter means and said tone detection means; (b) feature extraction means coupled to said buffer means for generating a set of numerical values for each spoken work, which numerial values are processed by a decision tree to identify the work spoken by the speaker.
Claim 23
Dependent Claim
26 words
The micropphone assembly defined by claim 6 wherein the other of said second and third microphones is for detecting sounds substantially emanating from the speaker's throat.
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) | 1991-01-04 | 1991-07-06 | 1992-01-05 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1995-01-04 | 1995-07-06 | 1996-01-05 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1999-01-04 | 1999-07-06 | 2000-01-05 | $7700.00 | Window Closed / Lapsed |