US5231670A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Voice controlled system and method for generating text from a voice controlled input
Assignee: Nuance Communications Inc
•
Filing: 1992-03-19
•
Granted: 1993-07-27
•
Expires: 2012-03-19
Abstract
Abstract Disclosed is a system and method for generating text from a voice input that divides the processing of each speech event into a dictation event and a text event. Each dictation event handles the processing of data relating to the input into the system, and each text event deals with the generation of text from the inputted voice signals. In order to easily distinguish the dictation events from each other and text events from each other the system and method creates a data structure for storing certain information relating to each individual event. Such data structures enable the system and method to process both simple spoken words as well as spoken commands and to provide the necessary text generation in response to the spoken words or to execute an appropriate function in response to a command. Speech recognition includes the ability to distinguish between dictation text and commands.
Inventors
- 👤 Richard S. Goldhor
- 👤 John F. Dooley
- 👤 Christopher N. Hume
- 👤 James P. Lerner
- 👤 Brian D. Wilson
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-31 22:49
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/08; G10L15/18; G06; G06F; G06F3/00; G06F3/16; G10L15/26; G10L15/1815; G10L15/06; G10L15/063; G10L2015/0631; G10L15/22; G10L2015/223
Claims Analysis
Total Claims: 27
Claim 1
Independent Claim
87 words
A system for editing displayed textual data generated in response to an audio input signal representing spoken input text, said system comprising: means for editing said generated textual data when said generated textual data is an incorrect translation of the spoken input text; means for distinguishing between audio input signals representing spoken input text and audio input signals representing spoken commands for editing said generated textual data; means for utilizing said audio input signals representing spoken commands to control said means for editing said generated textual data.
Claim 2
Independent Claim
87 words
A system for editing displayed textual data generated in response to an audio input signal representing spoken input text, said system comprising: means for editing said generated textual data when said generated textual data is an incorrect translation of the spoken input text; means for distinguishing between audio input signals representing spoken input text and audio input signals representing spoken commands for editing said generated textual data; means for utilizing said audio input signals representing spoken commands to control said means for editing said generated textual data.
Claim 3
Dependent Claim
105 words
The system for editing displayed textual data of claim 1 further comprising: a dictation event subsystem for processing speech events, a speech event being a word or set of words spoken by a user of the system, said dictation event subsystem including means for translating a speech event into textual data and means for recognizing a speech event representing a voice command and initiating operation in response to said command; a text event subsystem for receiving said translations as an input event from said dictation event subsystem and for processing said translations, said text event subsystem controlling the output from said system to an application.
Claim 4
Dependent Claim
47 words
The system for editing displayed textual data of claim 2 wherein said dictation event subsystem further comprises a dictation event database including a plurality of dictation event records and wherein said text event subsystem further comprises a text event subsystem comprising a plurality of text event records.
Claim 5
Dependent Claim
76 words
The system for editing displayed textual data of claim 3 wherein each of said dictation event records comprises: means for storing a unique identifier for each record; means for storing information regarding the chronological relationship of each record to other dictation event records in said dictation event database; means for storing an associated candidate set and a best match in the set for each speech event in response to which a dictation event record is created.
Claim 6
Dependent Claim
31 words
The system for editing displayed textual data of claim 2 wherein each of said dictation event record comprises: means for storing recognizer performance information; and means for storing recognizer state information.
Claim 7
Dependent Claim
23 words
The system for editing displayed textual data of claim 2 wherein each of said dictation event records comprises means for storing implementation-dependent information.
Claim 8
Dependent Claim
62 words
The system for editing displayed textual data of claim 2 wherein each of said text event records comprise: means for storing the chronological relationship of the text event to other text events; means for storing the hierarchical relationship of the text event record to other text event records; and means for storing the relationship of each input event to other input events.
Claim 9
Dependent Claim
47 words
The system for editing displayed textual data of claim 2 wherein each of said text event records of said text event database further comprises means for storing information regarding the type of input event that generated a translation leading to the creation of the text event record.
Claim 10
Dependent Claim
35 words
The system for editing displayed textual data of claim 2 wherein said text event record includes means for storing the state of an application to which said translations are transmitted from said text event subsystem.
Claim 11
Dependent Claim
61 words
The system for editing displayed textual data of claim 2 wherein said text event subsystem further comprises: means for creating a text event record in said text event database for each input event transmitted to said text event subsystem, said text event record including means for storing the associated dictation event identifier and a unique handle identifying the text event record.
Claim 12
Dependent Claim
75 words
The system for editing displayed textual data of claim 1 wherein said means for utilizing audio signals representing spoken commands to control said means for editing comprises means for processing a vocal "FILL IN FORM" command by supplying generated textual data to a field in a form having at least one blank field, said data being provided by the supplying of voice input or voice commands following the issuing of said "FILL IN FORM" command.
Claim 13
Dependent Claim
47 words
The system for editing displayed textual data of claim 1 further comprising means for generating a candidate set of textual data in response to each audio input signal or set of signals, each candidate in said set representing a likely textual representation of the spoken input text.
Claim 14
Dependent Claim
49 words
The system for editing displayed textual data of claim 12, further comprising means for correcting, by using a spoken command, incorrectly generated textual data by deleting incorrectly generated textual data from displayed textual data and choosing an alternative candidate of said candidates set to replace said deleted displayed text.
Claim 15
Dependent Claim
47 words
The system for editing displayed textual data of claim 13 wherein said means for choosing an alternative candidate comprises means for processing a vocal "TAKE N" command that causes said system to select the Nth listed candidate of said candidate set as the correctly generated textual data.
Claim 16
Dependent Claim
44 words
A system for editing displayed textual data of claim 13, wherein said means for utilizing said audio input signals representing spoken commands to control said means for editing said generated text comprises means for correcting, by spoken command, an incorrect generation of textual data.
Claim 17
Dependent Claim
36 words
The system for editing displayed textual data of claim 15, wherein said means for correcting incorrectly generated textual data comprises means for deleting incorrectly generated textual data from displayed textual data by using a spoken command.
Claim 18
Dependent Claim
34 words
The for editing displayed textual data of claim 16 wherein said means to delete comprises means for processing a vocal "SCRATCH THAT" command that causes the erasing of textual data generated by said system.
Claim 19
Dependent Claim
42 words
The system for editing displayed textual data of claim 15 wherein said means for correcting incorrectly generated textual data comprises means for processing a vocal "BACKTRACK" command that enables the system to remove one or more occurrences of incorrectly generated textual data.
Claim 20
Dependent Claim
56 words
The system for editing displayed textual data of claim 15 wherein said means for correcting incorrectly generated textual data of claim 15 comprises means for processing a vocal "TRY AGAIN" command that causes said system to reattempt to generate textual data without selecting the best match candidate originally selected as the candidate for that speech input.
Claim 21
Dependent Claim
48 words
The system for editing displayed textual data of claim 1, wherein said means for utilizing said audio input signals to control said means for editing comprises means for moving an input location of the textual data about the displayed textual data through the use of a spoken command.
Claim 22
Dependent Claim
52 words
The system for editing displayed textual data of claim 20 wherein said means for moving said input position comprises means for processing a vocal "FORWARD N" command that enables a current input location of the system to be shifted N positions forward from the position where said "FORWARD N" command is issued.
Claim 23
Independent Claim
73 words
A method for editing displayed textual data generated in response to an audio input signal representing spoken input text, said method comprising the steps of: editing said generated textual data by receiving audio signals representing spoken input textual data and spoken commands through an input device; analyzing said audio signals to determine whether said audio signals represent spoken input to be provided to an application or a spoken command for editing textual data.
Claim 24
Independent Claim
73 words
A method for editing displayed textual data generated in response to an audio input signal representing spoken input text, said method comprising the steps of: editing said generated textual data by receiving audio signals representing spoken input textual data and spoken commands through an input device; analyzing said audio signals to determine whether said audio signals represent spoken input to be provided to an application or a spoken command for editing textual data.
Claim 25
Dependent Claim
68 words
The method for editing displayed textual data of claim 22 wherein said step of editing further comprises the steps of: deriving candidate sets of textual data in response to each audio signal or set of audio signals; deleting incorrectly generated textual data by using a spoken command; replacing said incorrectly generated textual data with another candidate of textual data from said candidate set by using a spoken command.
Claim 26
Dependent Claim
36 words
The method for editing displayed textual data of claim 22, wherein said step of editing further comprises the step of moving the input position about said displayed textual data, through the use of a spoken command.
Claim 27
Dependent Claim
47 words
The method for editing textual data of claim 24, wherein said step of editing further comprises inserting spoken textual data into a textual data form by issuing a spoken command to move to a location in a form into which spoken input text is to be provided.
References Cited (Backward Citations)
US3418429A
Cited
US4144582A
Cited
US3846586A
Cited
US3989897A
Cited
US4661915A
Cited
US4435617A
Cited
US4468804A
Cited
US4545065A
Cited
US4507750A
Cited
US4520501A
Cited
US4630304A
Cited
US4829576A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1996-07-26 | 1997-01-25 | 1997-07-27 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-07-26 | 2001-01-25 | 2001-07-27 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-07-26 | 2005-01-25 | 2005-07-27 | $7700.00 | Window Closed / Lapsed |