US4158750A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Speech recognition system with delayed output
Assignee: NEC Corp
•
Filing: 1977-05-26
•
Granted: 1979-06-19
•
Expires: 1997-05-26
Abstract
Abstract In a speech recognition system of the type including a recognition unit responsive to a voice input and a conditioning input for recognizing the voice input to produce a recognition output, a start signal is produced whenever a voice input exceeds a threshold level and a pause interval detection signal is produced whenever a voice input falls below a threshold level. An output timing signal is produced when the detection signal lasts a preselected interval of time that may be either about 250 milliseconds or about 250 milliseconds plus a delay. The recognition output from the recognition unit produced in response to the detection signal is displayed in response also to the detection signal. The result is delivered to a utilization device in response to the output timing signal. The delay may be given either by a predetermined duration or an interval between those instants at which the above-mentioned 250 milliseconds have just elapsed after production of the detection signal and after production of another pause interval detection signal for a next following voice input. During the delay, it is possible either by a manually operable switch or a cancel voice input to cancel delivery of the recognition result displayed to be incorrect.
Inventors
- 👤 Hiroaki Sakoe
- 👤 Seibi Chiba
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-23 16:50
CPC Classifications
B; B60; B60R; B60R16/00; B60R16/02; B60R16/037; B60R16/0373; G; G10; G10L; G10L15/00; G10L25/00; G10L25/78; G10L25/87
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
180 words
In a speech recognition system of the type including recognition means responsive to a voice input and a conditioning input for recognizing said voice input to produce a recognition output representative of a result of recognition, said voice input including at least one brief pause interval and an end interval, said end interval defining the end of said voice input, wherein the improvement comprises beginning detection means responsive to said voice input for producing a start pulse representative of the beginning of said voice input, end detection means responsive to said voice input for producing a pause interval detection signal representative of at least one of said pause interval and said end interval and an end detection signal representative of said end interval, means for supplying said start pulse and said pause interval detection signal to said recognition means as said conditioning input, display means responsive to said pause interval detection signal and said recognition output for displaying said results of recognition, and output means responsive to said end detection signal for supplying said recognition output to a utilization device.
Claim 2
Dependent Claim
180 words
In a speech recognition system of the type including recognition means responsive to a voice input and a conditioning input for recognizing said voice input to produce a recognition output representative of a result of recognition, said voice input including at least one brief pause interval and an end interval, said end interval defining the end of said voice input, wherein the improvement comprises beginning detection means responsive to said voice input for producing a start pulse representative of the beginning of said voice input, end detection means responsive to said voice input for producing a pause interval detection signal representative of at least one of said pause interval and said end interval and an end detection signal representative of said end interval, means for supplying said start pulse and said pause interval detection signal to said recognition means as said conditioning input, display means responsive to said pause interval detection signal and said recognition output for displaying said results of recognition, and output means responsive to said end detection signal for supplying said recognition output to a utilization device.
Claim 3
Dependent Claim
230 words
In a speech recognition system of the type including recognition means responsive to an input electrical signal representative of a voice input and a conditioning input for recognizing said voice input to produce a recognition output representative of a result of recognition, said voice input including at least one brief pause interval and an end interval, said end interval defining the end of said voice input, wherein the improvement comprises beginning detection means responsive to said input electrical signal for producing a start pulse representative of the beginning of said voice input, pause interval detection means responsive to said input electrical signal and a predetermined threshold level for producing a pause interval detection signal representative of at least one of said pause interval and said end interval whenever the level of said input electrical signal is not higher than said threshold level, means for supplying said start pulse and said pause interval detection signal to said recognition means as said conditioning input, display means responsive to said pause interval detection signal and said recognition output for displaying said result of recognition, output control means responsive to said pause interval detection signal for producing an output timing signal only when said pause interval detection signal lasts at least a preselected interval of time, and output means responsive to said output timing signal for supplying said recognition output to a utilization device.
Claim 4
Dependent Claim
230 words
In a speech recognition system of the type including recognition means responsive to an input electrical signal representative of a voice input and a conditioning input for recognizing said voice input to produce a recognition output representative of a result of recognition, said voice input including at least one brief pause interval and an end interval, said end interval defining the end of said voice input, wherein the improvement comprises beginning detection means responsive to said input electrical signal for producing a start pulse representative of the beginning of said voice input, pause interval detection means responsive to said input electrical signal and a predetermined threshold level for producing a pause interval detection signal representative of at least one of said pause interval and said end interval whenever the level of said input electrical signal is not higher than said threshold level, means for supplying said start pulse and said pause interval detection signal to said recognition means as said conditioning input, display means responsive to said pause interval detection signal and said recognition output for displaying said result of recognition, output control means responsive to said pause interval detection signal for producing an output timing signal only when said pause interval detection signal lasts at least a preselected interval of time, and output means responsive to said output timing signal for supplying said recognition output to a utilization device.
Claim 5
Dependent Claim
68 words
A speech recognition system as claimed in claim 2 wherein said output control means comprises means responsive to said pause interval detection signal and a predetermined period of the order of 250 milliseconds serving as said preselected interval of time for producing a portion of said pause interval detection signal as said output timing signal only when said pause interval detection signal lasts at least said predetermined period.
Claim 6
Dependent Claim
226 words
A speech recognition system as claimed in claim 2 wherein said output control means comprises first means responsive to said pause interval detection signal and a predetermined period of the order of 250 milliseconds for producing an end detection pulse only when said pause interval detection signal lasts at least said predetermined period, second means for producing, when put into operation, a cancel pulse, two-state means put by a pulse of a first signal into a first state for producing an enabling signal and by a pulse of a second signal into a second state for not producing said enabling signal, third means for supplying said end detection pulse to said two-state means as a pulse of said first signal, fourth means for supplying said cancel pulse to said two-state means as a pulse of said second signal, logic means responsive to said enabling signal and the end detection pulse produced for a next following voice input for making the last-mentioned end detection pulse serve as a timing pulse only in the presence of said enabling signal, and fifth means for supplying said timing pulse to said output means as said output timing signal, whereby said preselected interval of time is rendered equal to said predetermined period plus an interval between those instants at which the first-mentioned and the last-mentioned end detection pulses are produced, respectively.
Claim 7
Dependent Claim
122 words
A speech recognition system as claimed in claim 4 wherein said output control means further comprises sixth means responsive to said enabling signal and a predetermined delay for producing an output pulse only when said enabling signal lasts at least said predetermined delay, said fourth means comprising means for supplying said output pulse to said two-state means as another pulse of said second signal, said fifth means comprising means for supplying said output pulse to said output means also as said output timing signal, whereby said preselected interval of time is rendered equal to said predetermined period plus said interval when said timing pulse is produced and equal to said predetermined period plus said predetermined delay when said output pulse is produced.
Claim 8
Dependent Claim
27 words
A speech recognition system as claimed in claim 5 wherein said second means comprises a manually operable switch that produces said cancel pulse when put into operation.
Claim 9
Dependent Claim
32 words
A speech recognition system as claimed in claim 5 wherein said second means comprises decoder means responsive to the recognition output produced for a predetermined voice input for producing said cancel pulse.
Claim 10
Dependent Claim
122 words
A speech recognition system as claimed in claim 7 wherein said decoder means comprises a decoder responsive to the recognition output produced for said predetermined voice input for producing a decoded output and a gate responsive to said decoded output and the end detection pulses produced for successive voice inputs for allowing only the end detection pulse produced for said predetermined voice input to pass therethrough to become said cancel pulse, said third means comprising another gate responsive to said decoded output and the end detection pulses produced for said successive voice inputs for supplying only the end detection pulses produced for the voice inputs other than said predetermined voice input to said two-state means as the pulses of said first signal.
References Cited (Backward Citations)
US3553372A
Cited
US4032710A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1982-06-18 | 1982-12-18 | 1983-06-19 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1986-06-18 | 1986-12-18 | 1987-06-19 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1990-06-18 | 1990-12-18 | 1991-06-19 | $7700.00 | Window Closed / Lapsed |