US6144938A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Voice user interface with personality
Assignee: Eloqui Voice Systems LLC
•
Filing: 1998-05-01
•
Granted: 2000-11-07
•
Expires: 2018-05-01
Abstract
Abstract The present invention provides a voice user interface with personality. In one embodiment, a method includes executing a voice user interface, and controlling the voice user interface to provide the voice user interface with a personality. The method includes selecting a prompt based on various context situations, such as a previously selected prompt and the user's experience with using the voice user interface.
Inventors
- 👤 Kevin J. Surace
- 👤 George M. White
- 👤 Byron B. Reeves
- 👤 Clifford I. Nass
- 👤 Mark D. Campbell
- 👤 Roy D. Albert
- 👤 James P. Giangola
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-05 19:17
CPC Classifications
H; H04; H04M; H04M3/00; H04M3/42; H04M3/487; H04M3/493; H04M3/4936; G; G10; G10L; G10L13/00; G10L13/02; G10L13/033; G10L15/00; G10L15/08; G10L15/18; G10L15/183; G10L15/19; G10L15/22; G10L2015/226; G10L2015/227; H04M2201/00; H04M2201/40; H04M2201/60; H04M2203/00; H04M2203/35; H04M2203/355; H04M3/50; H04M3/53; H04M3/533; H04M3/53366; H04M3/53383
Claims Analysis
Total Claims: 105
Claim 1
Independent Claim
108 words
An apparatus for a voice user interface with personality, the apparatus comprising: logic that provides a voice user interface, the voice user interface outputting first voice signals, and the voice user interface recognizing speech signals; logic that provides a personality, the logic that provides the personality interfacing with the logic that provides the voice user interface to provide the voice user interface with a verbal personality; and a recognition grammar stored in a memory, the recognition grammar comprising multiple phrases that a virtual assistant with a personality can recognize when spoken by a user, and the recognition grammar being selected based on the personality of the virtual assistant.
Claim 2
Independent Claim
108 words
An apparatus for a voice user interface with personality, the apparatus comprising: logic that provides a voice user interface, the voice user interface outputting first voice signals, and the voice user interface recognizing speech signals; logic that provides a personality, the logic that provides the personality interfacing with the logic that provides the voice user interface to provide the voice user interface with a verbal personality; and a recognition grammar stored in a memory, the recognition grammar comprising multiple phrases that a virtual assistant with a personality can recognize when spoken by a user, and the recognition grammar being selected based on the personality of the virtual assistant.
Claim 3
Dependent Claim
46 words
The apparatus as recited in claim 1 wherein the logic that provides the voice user interface and the logic that provides the personality comprise computer software stored in a memory of a computer system, the computer software being executed on a processor of the computer system.
Claim 4
Dependent Claim
34 words
The apparatus as recited in claim 2 wherein the computer system comprises a microphone and speaker, the speech signals being received from the microphone, and the first voice signals being transmitted to the speaker.
Claim 5
Dependent Claim
35 words
The apparatus as recited in claim 2 wherein the computer system is in communication with a telephone, the speech signals being received from the telephone, and the first voice signals being transmitted to the telephone.
Claim 6
Dependent Claim
16 words
The apparatus as recited in claim 2 wherein the computer system comprises at least two computers.
Claim 7
Dependent Claim
43 words
The apparatus as recited in claim 2 wherein the computer system comprises: a telephone line card in communication with a telephone line for receiving speech input data from a user and speech output data from the logic that provides the voice user interface.
Claim 8
Dependent Claim
24 words
The apparatus as recited in claim 6 wherein the computer system further comprises: a network card, the network card in communication with a network.
Claim 9
Dependent Claim
20 words
The apparatus as recited in claim 1 wherein the voice user interface with personality comprises a virtual assistant with personality.
Claim 10
Dependent Claim
38 words
The apparatus as recited in claim 8 wherein the personality of the virtual assistant comprises a predetermined tone or cadence of the first voice signals, a predetermined vocabulary, a predetermined sentence construction, or a predetermined degree of assertiveness.
Claim 11
Dependent Claim
26 words
The apparatus as recited in claim 8 wherein the first voice signals comprise a prompt, the prompt being scripted for the personality of the virtual assistant.
Claim 12
Dependent Claim
30 words
The apparatus as recited in claim 8 wherein the first voice signals comprise a recorded prompt, the recorded prompt being acted and recorded for the personality of the virtual assistant.
Claim 13
Dependent Claim
28 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises randomly selecting a prompt from multiple prompts available to provide a predetermined response.
Claim 14
Dependent Claim
25 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises selecting a prompt, the prompt comprising an appropriate temporal prompt.
Claim 15
Dependent Claim
34 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises selecting a prompt, the prompt comprising a term that was previously spoken by the user in a recognized command.
Claim 16
Dependent Claim
25 words
The apparatus as recited in claim 1 wherein the logic that provides the voice user interface comprises recognizing multiple spoken commands as a predetermined command.
Claim 17
Dependent Claim
33 words
The apparatus as recited in claim 1 wherein the logic that provides the voice user interface comprises generating second voice signals, the second voice signals comprising synthesized voice signals that correspond to text.
Claim 18
Dependent Claim
48 words
The apparatus as recited in claim 1 wherein the logic that provides the personality selects a smooth hand-off prompt to provide a smooth hand-off between the first voice signals and second voice signals, the second voice signals being output by the logic that provides the voice user interface.
Claim 19
Dependent Claim
38 words
The apparatus as recited in claim 17 wherein the logic that provides the personality selects a first complete sentence for output by the first voice signals and a second complete sentence for output by the second voice signals.
Claim 20
Dependent Claim
34 words
The apparatus as recited in claim 18 wherein the first voice signals comprise the voice of a virtual assistant, and the second voice signals comprise the voice of a helper to the virtual assistant.
Claim 21
Dependent Claim
16 words
The apparatus as recited in claim 19 wherein the second voice signals comprise recorded voice signals.
Claim 22
Dependent Claim
16 words
The apparatus as recited in claim 19 wherein the second voice signals comprise synthesized voice signals.
Claim 23
Dependent Claim
51 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises controlling the selection of the first voice signals output by the voice user interface such that the voice user interface with personality behaves consistently with social and emotional norms, including politeness, while interacting with the user.
Claim 24
Dependent Claim
26 words
The apparatus as recited in claim 22 wherein the first voice signals comprise a word that is within a recognition grammar of the voice user interface.
Claim 25
Dependent Claim
47 words
The apparatus as recited in claim 22 wherein the logic that provides the personality comprises controlling the selection of the first voice signals output by the voice user interface such that the voice user interface with personality addresses a user by a proper name of the user.
Claim 26
Dependent Claim
45 words
The apparatus as recited in claim 22 wherein the voice user interface with personality suggests responses available to the user that are polite and socially appropriate, thereby permitting the user to be polite and socially appropriate while interacting with the voice user interface with personality.
Claim 27
Dependent Claim
28 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises controlling the voice user interface in situations in which negative comments are needed.
Claim 28
Dependent Claim
48 words
The apparatus as recited in claim 26 wherein the logic that provides the personality comprises selecting a negative prompt, the negative prompt comprising a concise and plain statement of a problem without blaming a user, and outputting a recording of the brief negative prompt at a lower volume.
Claim 29
Dependent Claim
36 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises selecting a prompt based on a user's experience with using the voice user interface during a current session and across sessions.
Claim 30
Dependent Claim
37 words
The apparatus as recited in claim 28 wherein the logic that provides the personality comprises selecting a shorter prompt based on the user's experience with using the voice user interface during the current session and across sessions.
Claim 31
Dependent Claim
37 words
The apparatus as recited in claim 28 wherein the logic that provides the personality comprises selecting a longer help prompt if the user's input indicates a problem with increasing frequency during the current session and across sessions.
Claim 32
Dependent Claim
53 words
The apparatus as recited in claim 28 wherein the logic that provides the personality comprises selecting a prompt that provides the available options to the user if the voice user interface does not recognize a command spoken by the user or if the user has not spoken for a defined period of time.
Claim 33
Dependent Claim
54 words
The apparatus as recited in claim 28 wherein the logic that provides the personality comprises selecting a coaching prompt that provides a current state of interaction, provides commands that the user can say at the current state of interaction, and provides the actions that would be taken in response to each of the commands.
Claim 34
Dependent Claim
19 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises selecting an approximation prompt.
Claim 35
Dependent Claim
28 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises providing the voice user interface with a first personality and a second personality.
Claim 36
Dependent Claim
30 words
The apparatus as recited in claim 34 wherein the first voice signals comprise the voice of the first personality, and second voice signals comprise the voice of the second personality.
Claim 37
Dependent Claim
26 words
The apparatus as recited in claim 34 wherein a first virtual assistant comprises the first personality, and a second virtual assistant comprise s the second personality.
Claim 38
Dependent Claim
20 words
The apparatus as recited in claim 36 wherein the first virtual assistant and the second virtual assistant comprise different genders.
Claim 39
Dependent Claim
47 words
The apparatus as recited in claim 36 wherein a user selects the first virtual assistant or the second virtual assistant based on descriptions of the first virtual assistant and the second virtual assistant or based on interacting with the first virtual assistant and the second virtual assistant.
Claim 40
Dependent Claim
19 words
The apparatus as recited in claim 1 wherein the logic that provides the personality comprises selecting a humorous prompt.
Claim 41
Dependent Claim
23 words
The apparatus as recited in claim 1 wherein the voice user interface with personality comprises a virtual assistant for a voice-based desktop environment.
Claim 42
Dependent Claim
26 words
The apparatus as recited in claim 40 wherein the desktop environment comprises multiple objects, the virtual assistant being navigated among the multiple objects by a user.
Claim 43
Dependent Claim
38 words
The apparatus as recited in claim 1 wherein the logic that provides the voice user interface comprises: echo cancellation software, barge-in software, signal processing software, automatic speech recognition/natural language software, request for services software, and text-to-speech/recorded speech software.
Claim 44
Independent Claim
88 words
A method for a voice user interface with personality, the method comprising: storing a recognition grammar in a memory, the recognition grammar comprising multiple phrases that a virtual assistant with a personality can recognize when spoken by a user, the recognition grammar being selected based on the personality of the virtual assistant; executing a voice user interface, the voice user interface outputting first voice signals, the voice user interface recognizing speech signals; and controlling the voice user interface to provide the voice user interface with a verbal personality.
Claim 45
Independent Claim
88 words
A method for a voice user interface with personality, the method comprising: storing a recognition grammar in a memory, the recognition grammar comprising multiple phrases that a virtual assistant with a personality can recognize when spoken by a user, the recognition grammar being selected based on the personality of the virtual assistant; executing a voice user interface, the voice user interface outputting first voice signals, the voice user interface recognizing speech signals; and controlling the voice user interface to provide the voice user interface with a verbal personality.
Claim 46
Dependent Claim
37 words
The method as recited in claim 43 wherein the voice user interface with personality comprises computer software stored in the memory of a computer system, the computer software being executed on a processor of the computer system.
Claim 47
Dependent Claim
20 words
The method as recited in claim 43 wherein the voice user interface with personality comprises a virtual assistant with personality.
Claim 48
Dependent Claim
33 words
The method as recited in claim 45 wherein the personality of the virtual assistant comprises a predetermined tone or cadence, a predetermined vocabulary, a predetermined sentence construction, or a predetermined degree of assertiveness.
Claim 49
Dependent Claim
27 words
The method as recited in claim 43 wherein the first voice signals comprise a prompt, the prompt being scripted for the personality of the voice user interface.
Claim 50
Dependent Claim
31 words
The method as recited in claim 43 wherein the first voice signals comprise a recorded prompt, the recorded prompt being acted and recorded for the personality of the voice user interface.
Claim 51
Dependent Claim
26 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises randomly selecting a specific prompt that corresponds to a generic prompt.
Claim 52
Dependent Claim
25 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises selecting a prompt, the prompt comprising an appropriate temporal prompt.
Claim 53
Dependent Claim
39 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises selecting a prompt to respond to a user, the prompt comprising a term that was previously spoken by the user in a recognized command.
Claim 54
Dependent Claim
21 words
The method as recited in claim 43 wherein the voice user interface comprises recognizing multiple spoken commands as a predetermined command.
Claim 55
Dependent Claim
29 words
The method as recited in claim 43 wherein the voice user interface comprises generating second voice signals, the second voice signals comprising synthesized voice signals that correspond to text.
Claim 56
Dependent Claim
45 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises selecting a smooth hand-off prompt that provides a smooth hand-off between the first voice signals and second voice signals, the second voice signals being output by the voice user interface.
Claim 57
Dependent Claim
39 words
The method as recited in claim 54 wherein the controlling the voice user interface comprises selecting a first complete sentence for output by the first voice signals and a second complete sentence for output by the second voice signals.
Claim 58
Dependent Claim
34 words
The method as recited in claim 55 wherein the first voice signals comprise the voice of a virtual assistant and the second voice signals comprise the voice of a helper to the virtual assistant.
Claim 59
Dependent Claim
16 words
The method as recited in claim 56 wherein the second voice signals comprise recorded voice signals.
Claim 60
Dependent Claim
16 words
The method as recited in claim 56 wherein the second voice signals comprise synthesized voice signals.
Claim 61
Dependent Claim
49 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises controlling the selection of the first voice signals output by the voice user interface such that the voice user interface behaves consistently with social and emotional norms, including politeness, while interacting with the user.
Claim 62
Dependent Claim
32 words
The method as recited in claim 59 wherein the controlling the voice user interface comprises selecting a word that is within the recognition grammar to be output by the first voice signals.
Claim 63
Dependent Claim
45 words
The method as recited in claim 59 wherein the controlling the voice user interface comprises controlling the selection of the first voice signals output by the voice user interface such that the voice user interface addresses a user by a proper name of the user.
Claim 64
Dependent Claim
16 words
The method as recited in claim 59 wherein the speech signals comprise user commands spoken politely.
Claim 65
Dependent Claim
28 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises controlling the voice user interface in situations in which negative comments are needed.
Claim 66
Dependent Claim
31 words
The method as recited in claim 63 wherein the controlling the voice user interface comprises selecting a negative prompt, and outputting a recording of the negative prompt at a lower volume.
Claim 67
Dependent Claim
36 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises selecting a prompt based on a user's experience with using the voice user interface during a current session and across sessions.
Claim 68
Dependent Claim
37 words
The method as recited in claim 65 wherein the controlling the voice user interface comprises selecting a shorter prompt based on the user's experience with using the voice user interface during the current session and across sessions.
Claim 69
Dependent Claim
37 words
The method as recited in claim 65 wherein the controlling the voice user interface comprises selecting a longer help prompt if the user's input indicates a problem with increasing frequency during the current session and across sessions.
Claim 70
Dependent Claim
53 words
The method as recited in claim 65 wherein the controlling the voice user interface comprises selecting a prompt that lists the available options to the user if the voice user interface does not recognize a command spoken by the user or if the user has not spoken for a defined period of time.
Claim 71
Dependent Claim
54 words
The method as recited in claim 65 wherein the controlling the voice user interface comprises selecting a coaching prompt that provides a current state of interaction, lists commands that the user can say at the current state of interaction, and lists the actions that would be taken in response to each of the commands.
Claim 72
Dependent Claim
19 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises selecting an approximation prompt.
Claim 73
Dependent Claim
28 words
The method as recited in claim 43 wherein the controlling the voice user interface comprises providing the voice user interface with a first personality and a second personality.
Claim 74
Dependent Claim
30 words
The method as recited in claim 71 wherein the first voice signals comprise the voice of the first personality, and second voice signals comprise the voice of the second personality.
Claim 75
Dependent Claim
25 words
The method as recited in claim 71 wherein a first virtual assistant comprises the first personality, and a second virtual assistant comprises the second personality.
Claim 76
Dependent Claim
20 words
The method as recited in claim 73 wherein the first virtual assistant and the second virtual assistant comprise different genders.
Claim 77
Dependent Claim
47 words
The method as recited in claim 73 wherein a user selects the first virtual assistant or the second virtual assistant based on descriptions of the first virtual assistant and the second virtual assistant or based on interacting with the first virtual assistant and the second virtual assistant.
Claim 78
Dependent Claim
19 words
The method as recited in claim 43 wherein the voice user interface with personality comprises selecting a humorous prompt.
Claim 79
Dependent Claim
23 words
The method as recited in claim 43 wherein the voice user interface with personality comprises a virtual assistant for a voice-based desktop environment.
Claim 80
Dependent Claim
26 words
The method as recited in claim 77 wherein the desktop environment comprises multiple objects, the virtual assistant being navigated among the multiple objects by a user.
Claim 81
Dependent Claim
34 words
The method as recited in claim 43 wherein the voice user interface comprises: echo cancellation software, barge-in software, signal processing software, automatic speech recognition/natural language software, request for services software, and text-to-speech/recorded speech software.
Claim 82
Dependent Claim
98 words
A data signal in a carrier wave for a voice user interface with personality, the data signal in a carrier wave comprising: first voice signals, the first voice signals being output by a voice user interface with a verbal personality; and speech signals, the voice user interface with a verbal personality recognizing the speech signals using a recognition grammar, the recognition grammar being stored in a memory and comprising multiple phrases that a virtual assistant with a personality can recognize when spoken by a user, the recognition grammar being selected based on the personality of the virtual assistant.
Claim 83
Dependent Claim
98 words
A data signal in a carrier wave for a voice user interface with personality, the data signal in a carrier wave comprising: first voice signals, the first voice signals being output by a voice user interface with a verbal personality; and speech signals, the voice user interface with a verbal personality recognizing the speech signals using a recognition grammar, the recognition grammar being stored in a memory and comprising multiple phrases that a virtual assistant with a personality can recognize when spoken by a user, the recognition grammar being selected based on the personality of the virtual assistant.
Claim 84
Dependent Claim
32 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a prompt, the prompt being scripted for the personality of the voice user interface.
Claim 85
Dependent Claim
36 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a recorded prompt, the recorded prompt being acted and recorded for the personality of the voice user interface.
Claim 86
Dependent Claim
31 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a prompt randomly selected from multiple prompts available to provide a predetermined response.
Claim 87
Dependent Claim
27 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a prompt, the prompt comprising an appropriate temporal prompt.
Claim 88
Dependent Claim
41 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a prompt to respond to a user, the prompt comprising a term that was previously spoken by the user in a recognized command.
Claim 89
Dependent Claim
34 words
The data signal in a carrier wave as recited in claim 80 wherein the speech signals comprise a phrase, the phrase being recognized by the voice user interface with personality as a predetermined command.
Claim 90
Dependent Claim
30 words
The data signal in a carrier wave as recited in claim 80 further comprising: second voice signals, the second voice signals being output by the voice user interface with personality.
Claim 91
Dependent Claim
48 words
The data signal in a carrier wave as recited in claim 87 further comprising: third voice signals, the third voice signals being output by the voice user interface with personality, the third voice signals comprising a smooth hand-off between the first voice signals and the second voice signals.
Claim 92
Dependent Claim
32 words
The data signal in a carrier wave as recited in claim 87 wherein the first voice signals comprise a first complete sentence and the second voice signals comprise a second complete sentence.
Claim 93
Dependent Claim
39 words
The data signal in a carrier wave as recited in claim 87 wherein the first voice signals comprise the voice of the virtual assistant, and the second voice signals comprise the voice of a helper to the virtual assistant.
Claim 94
Dependent Claim
21 words
The data signal in a carrier wave as recited in claim 87 wherein the second voice signals comprise synthesized voice signals.
Claim 95
Dependent Claim
33 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a word that is within the recognition grammar of the voice user interface with personality.
Claim 96
Dependent Claim
24 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a proper name of the user.
Claim 97
Dependent Claim
48 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a negative prompt, the negative prompt comprising a concise and plain statement of a problem without blaming a user, and the first voice signals being output at a lower volume.
Claim 98
Dependent Claim
43 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a prompt that is selected based on a user's experience with using the voice user interface with personality during a current session and across sessions.
Claim 99
Dependent Claim
39 words
The data signal in a carrier wave as recited in claim 95 wherein the first voice signals comprise a longer help prompt if the user's input indicates a problem with increasing frequency during the current session and across sessions.
Claim 100
Dependent Claim
56 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a coaching prompt that provides a current state of interaction, lists commands that the user can say at the current state of interaction, and lists the actions that would be taken in response to each of the commands.
Claim 101
Dependent Claim
21 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise an approximation prompt.
Claim 102
Dependent Claim
27 words
The data signal in a carrier wave as recited in claim 80 wherein the voice user interface with personality comprises a first personality and a second personality.
Claim 103
Dependent Claim
48 words
The data signal in a carrier wave as recited in claim 99 wherein the first voice signals comprise the voice of the first personality, and second voice signals comprise the voice of the second personality, the second voice signals being output by the voice user interface with personality.
Claim 104
Dependent Claim
30 words
The data signal in a carrier wave as recited in claim 99 wherein a first virtual assistant comprises the first personality, and a second virtual assistant comprises the second personality.
Claim 105
Dependent Claim
21 words
The data signal in a carrier wave as recited in claim 80 wherein the first voice signals comprise a humorous prompt.
References Cited (Backward Citations)
US5367454A
Cited
US5559927A
Cited
US5636325A
Cited
US5860064A
Cited
US5500920A
Cited
EP0697780A2
Cited
WO1996011542A2
Cited
US5873057A
Cited
WO1997033416A1
Cited
US5987415A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-11-07 | 2004-05-08 | 2004-11-07 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-11-07 | 2008-05-08 | 2008-11-07 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-11-07 | 2012-05-08 | 2012-11-07 | $7700.00 | Window Closed / Lapsed |