Mode confidence
A method for managing an interactive dialog between a machine and a user is claimed. In one embodiment, a confidence value is determined in response to an input provided by the user or an environment of the user. The confidence value can be utilized to determine the mode and the verbalization of a desired sequence of spoken phrases. The input provided by the user can be audio input or touch tone input. The desired sequence of spoken phrases can comprise instructions encouraging a user to use audio input, touch tone input or both. In another embodiment, the confidence value can be further affected by: input exit conditions; speech onset timings; duration of audio input; or a model of user attention.
1 . A method for managing interactive dialog between a machine and a user comprising:
verbalizing at least one desired sequence of one or more spoken phrases;
enabling a user to hear the at least one desired sequence of spoken phrases;
receiving input from the user or an environment of the user;
determining at least one confidence value in response to an input from the user or an environment of the user; and
wherein the at least one confidence value is utilized to determine the mode and verbalization of at least one subsequent desired sequence of one or more spoken phrases.
2 . The method of claim 1 , wherein the at least one confidence value comprises a plurality of discrete states, wherein each discrete state is associated with a different confidence value.
3 . The method of claim 2 , wherein each discrete state affects the mode and verbalization of the at least one subsequent desired sequence of one or more spoken phrases.
4 . The method of claim 1 , wherein the input from a user or an environment of a user is touch tone or audio input.
5 . The method of claim 4 , wherein the at least one desired sequence of spoken phrases further comprises:
instructions that encourage a user to provide audio input;
instructions that encourage a user to provide touch tone input; or
instructions that encourage a user to provide audio input or touch tone input.
6 . The method of claim 5 , wherein the instructions that encourage a user to provide audio input or touch tone input are in response to at least one intermediate confidence value.
7 . The method of claim 1 , wherein the at least one confidence value is further affected by:
turn-taking confidence in response to the input from the user;
speech duration confidence in response to the input from the user; or
state-completion confidence in response to the input from the user.
8 . The method of claim 1 , wherein the at least one confidence value is further affected by:
input exit conditions;
speech onset timings;
durations of possible spoken utterances; or
a model of user attention.
9 . A system for managing interactive dialog between a machine and a user comprising:
means for verbalizing at least one desired sequence of one or more spoken phrases;
means for enabling a user to hear the at least one desired sequence of spoken phrases;
means for receiving input from the user or an environment of the user;
means for determining at least one confidence value in response to an input from the user or an environment of the user; and
wherein the at least one confidence value is utilized to determine the mode and verbalization of at least one subsequent desired sequence of one or more spoken phrases.
10 . The system of claim 9 , wherein the at least one confidence value comprises a plurality of discrete states, wherein each discrete state is associated with a different confidence value.
11 . The system of claim 10 , wherein each discrete state affects the mode and verbalization of the at least one subsequent desired sequence of one or more spoken phrases.
12 . The method of claim 9 , wherein the input from a user or an environment of a user is touch tone or audio input.
13 . The method of claim 12 , wherein the at least one desired sequence of spoken phrases further comprises:
instructions that encourage a user to provide audio input;
instructions that encourage a user to provide touch tone input; or
instructions that encourage a user to provide audio input or touch tone input.
14 . The method of claim 13 , wherein the instructions that encourage a user to provide audio input or touch tone input are in response to at least one intermediate confidence value.
15 . The method of claim 9 , wherein the at least one confidence value is further affected by:
turn-taking confidence in response to the input from the user;
speech duration confidence in response to the input from the user; or
state-completion confidence in response to the input from the user.
16 . The method of claim 9 , wherein the at least one confidence value is further affected by:
input exit conditions;
speech onset timings;
durations of possible spoken utterances; or
a model of user attention.
17 . A computer program product for managing interactive dialog between a machine and a user, wherein the computer program product comprises computer code stored on a computer-readable medium, the computer program product comprising:
computer code for verbalizing at least one desired sequence of one or more spoken phrases;
computer code for enabling a user to hear the at least one desired sequence of spoken phrases;
computer code for receiving input from the user or an environment of the user;
computer code for determining at least one confidence value in response to an input from the user or an environment of the user; and
wherein the at least one confidence value is utilized to determine the mode and verbalization of at least one subsequent desired sequence of one or more spoken phrases.
18 . The computer program product of claim 17 , wherein the input from a user or an environment of a user is touch tone or audio input.
19 . The computer program product of claim 18 , wherein the at least one desired sequence of spoken phrases further comprises:
instructions that encourage a user to provide audio input;
instructions that encourage a user to provide touch tone input; or
instructions that encourage a user to provide audio input or touch tone input.
20 . The computer program product of claim 19 , wherein the at least one confidence value is further affected by:
input exit conditions;
speech onset timings;
durations of possible spoken utterances; or
a model of user attention.