Method of implicit confirmation for automatic speech recognition
First Claim
1. A method of determining, in an automated speech recognition apparatus for identifying in user speech using a speech recognition technique and for executing, as a data processing instruction, a user-issued verbal command using a user-selected one of a plurality of associated command operators defining a command operators set and stored in a memory, whether to execute the verbal command which has been identified by the recognition apparatus in the user speech, comprising the steps of:
- (A) identifying, in the speech recognition apparatus, a verbal command in user speech as a user-issued verbal command to the speech recognition apparatus;
(B) upon said identifying of the verbal command, starting a timer defining a predetermined time-out period and issuing, substantially concurrent with said starting of the timer, a user-perceptible indication that the speech recognition apparatus is awaiting receipt of a user-issued command operator associated with the identified verbal command;
(C) retrieving from the memory the command operators set associated with the identified verbal command;
(D) monitoring, in the speech recognition apparatus during the time-out period of the timer, user speech to identify in the user speech one of the command operators of the retrieved command operator set in the user speech during the time-out period, and(i) where one of the associated command operators is identified by the speech recognition apparatus in the user speech during the time-out period of the timer, executing as a data processing instruction the identified user-issued verbal command using the one of the associated command operators identified in the speech recognition apparatus, and(ii) where none of the plural command operators in the retrieved command operators set is identified by the speech recognition apparatus in the user speech during the time-out period, resetting the speech recognition apparatus at the end of the time-out period to await receipt and identification by the speech recognition apparatus of a subsequent user-issued verbal command.
6 Assignments
0 Petitions
Accused Products
Abstract
A method for automatically confirming verbal commands issued by a user and received by an automatic speech recognition system. Each verbal command is associated with a command operator set in which one or more command operators are stored. After the user vocalizes a recognized verbal command, the automatic speech recognition system awaits vocalization of a valid command operator from an associated stored command operator set for a pre-determined period of time. During this waiting period a non-intrusive indicator such as a light or a low volume tone notifies the user that the automatic speech recognition system is awaiting or ready to receive an appropriate command operator. If the user vocalizes a valid and recognized command operator during the waiting period, then the automatic speech recognition system executes the verbal command using the command operator and issues a confirmation to the user that the verbal command has been executed. Otherwise, the automatic speech recognition system returns to its idle state awaiting a further verbal command.
208 Citations
5 Claims
-
1. A method of determining, in an automated speech recognition apparatus for identifying in user speech using a speech recognition technique and for executing, as a data processing instruction, a user-issued verbal command using a user-selected one of a plurality of associated command operators defining a command operators set and stored in a memory, whether to execute the verbal command which has been identified by the recognition apparatus in the user speech, comprising the steps of:
-
(A) identifying, in the speech recognition apparatus, a verbal command in user speech as a user-issued verbal command to the speech recognition apparatus; (B) upon said identifying of the verbal command, starting a timer defining a predetermined time-out period and issuing, substantially concurrent with said starting of the timer, a user-perceptible indication that the speech recognition apparatus is awaiting receipt of a user-issued command operator associated with the identified verbal command; (C) retrieving from the memory the command operators set associated with the identified verbal command; (D) monitoring, in the speech recognition apparatus during the time-out period of the timer, user speech to identify in the user speech one of the command operators of the retrieved command operator set in the user speech during the time-out period, and (i) where one of the associated command operators is identified by the speech recognition apparatus in the user speech during the time-out period of the timer, executing as a data processing instruction the identified user-issued verbal command using the one of the associated command operators identified in the speech recognition apparatus, and (ii) where none of the plural command operators in the retrieved command operators set is identified by the speech recognition apparatus in the user speech during the time-out period, resetting the speech recognition apparatus at the end of the time-out period to await receipt and identification by the speech recognition apparatus of a subsequent user-issued verbal command.
-
-
2. A method of determining, in an automated speech recognition apparatus for identifying in user speech using a speech recognition technique and for executing, as a data processing instruction, a user-issued verbal command using a user-selected one of a plurality of associated command operators defining a command operators set and stored in a memory, whether to execute the verbal command which has been identified by the recognition apparatus in the user speech, comprising the steps of:
-
(A) identifying, in the speech recognition apparatus, a verbal command in user speech as a user-issued verbal command to the speech recognition apparatus; (B) upon said identifying of the verbal command, starting a timer defining a predetermined time-out period and issuing, substantially concurrent with said starting of the timer, a user-perceptible indication that the speech recognition apparatus is awaiting receipt of a user-issued command operator associated with the identified verbal command; (C) monitoring, in the speech recognition apparatus during the time-out period of the timer, user speech to identify in the user speech during the time-out period one of the command operators of the stored command operator set associated with the identified verbal command, and (i) where one of the associated command operators is identified by the speech recognition apparatus in the user speech during the time-out period of the timer, executing as a data processing instruction the identified user-issued verbal command using the one of the associated command operators identified in the speech recognition apparatus, and (ii) where none of the plural command operators in the retrieved command operators set is identified by the speech recognition apparatus in the user speech during the time-out period, resetting the speech recognition apparatus at the end of the time-out period to thereafter await receipt and identification by the speech recognition apparatus of a subsequent user-issued verbal command.
-
-
3. A method for automated confirmation of predetermined verbal commands issued by a user and received by an automated speech recognition apparatus having a memory and operable to apply a speech recognition technique and to execute data processing instructions, each verbal command having an associated operator set stored in the memory, wherein each verbal command comprises a command segment and an operator segment selected from the associated operator set, and wherein each verbal command defines to a data-processing instruction, said method comprising the steps of:
-
(a) waiting, by the apparatus, to receive a user vocalized first utterance; (b) receiving, in the apparatus the user vocalized first utterance; (c) applying, in the apparatus the speech recognition technique to the first utterance to identify in the first utterance a command segment; (d) retrieving the command set associated with the identified command segment from the memory of the apparatus when the first utterance is a command segment, and returning to said step (a) otherwise; (e) after said retrieving of the command set initializing, by the apparatus, a timer having a timing value of a predetermined maximum duration and activating, substantially concurrent with said initialization of the timer, an indicator to inform the user that the apparatus is ready to receive a user vocalized operator segment; (f) determining, by the apparatus following said initialization of the timer, whether the apparatus has received a user vocalized second utterance during a predetermined timing interval less than said predetermined maximum duration, and; (1) when a vocalized second utterance has been received by the apparatus, applying, in the apparatus the speech recognition technique to the second utterance to identify an operator segment in the second utterance vocalized by the user during the timing interval; (2) incrementing the timing value of the timer by the timing interval when an operator segment is not received during the timing interval; and (3) comparing the timing value to the maximum duration and returning to said step (a) when the timing value is at least equal to the maximum duration and returning to said step (e) when the timing value is less than the maximum duration; (g) analyzing the received vocalized command segment and the operator segment to identify the data processing instruction corresponding to the received vocalized command segment; and (h) executing the data-processing instruction defined by the command segment and the operator segment. - View Dependent Claims (4, 5)
-
Specification