Apparatus and method for speech recognition
First Claim
1. An apparatus for speech recognition, comprising:
- a display device including a screen configured to display a plurality of domains including a general domain and at least one another domain that are selectable by a user to support recognition of a speech, the general domain being associated with a database to be referenced to support the recognition of the speech using all subject matter areas and the at least one other domain being associated with a different database than the database of the general domain to be referenced to support the recognition of the speech using a specific subject matter area;
a user input device including at least one of a microphone, a touch screen, a keyboard, and a mouse configured to receive a selection of at least one domain from among the plurality of domains displayed by the user; and
a communicator including an antenna configured to transmit information regarding the selection by the user of the at least one domain,wherein while the display device is displaying the plurality of domains, at least one of the plurality of domains is displayed with emphasis when information obtained in relation to a situation of the user indicates relation to the at least one of the plurality of domains to assist the user in the selection of at least one domain from among the plurality of domains,wherein the general domain and the at least one other domain are configured to have a hierarchical structure, andwherein a sentence is constructed using the at least one domain selected by the user in the selection to exemplify a level of recognizability of the speech according to the at least one domain selected by the user.
1 Assignment
0 Petitions
Accused Products
Abstract
Disclosed is an apparatus for speech recognition and automatic translation operated in a PC or a mobile device. The apparatus for speech recognition according to the present invention includes a display unit that displays a screen for selecting a domain as a unit for a speech recognition region previously sorted for speech recognition to a user; a user input unit that receives a selection of a domain from the user; and a communication unit that transmits the user selection information for the domain. According to the present invention, the apparatus for speech recognition using an intuitive and simple user interface is provided to a user to enable the user to easily select/correct a designation domain of a speech recognition system and improve accuracy and performance of speech recognition and automatic translation by the designated system for speech recognition.
31 Citations
19 Claims
-
1. An apparatus for speech recognition, comprising:
-
a display device including a screen configured to display a plurality of domains including a general domain and at least one another domain that are selectable by a user to support recognition of a speech, the general domain being associated with a database to be referenced to support the recognition of the speech using all subject matter areas and the at least one other domain being associated with a different database than the database of the general domain to be referenced to support the recognition of the speech using a specific subject matter area; a user input device including at least one of a microphone, a touch screen, a keyboard, and a mouse configured to receive a selection of at least one domain from among the plurality of domains displayed by the user; and a communicator including an antenna configured to transmit information regarding the selection by the user of the at least one domain, wherein while the display device is displaying the plurality of domains, at least one of the plurality of domains is displayed with emphasis when information obtained in relation to a situation of the user indicates relation to the at least one of the plurality of domains to assist the user in the selection of at least one domain from among the plurality of domains, wherein the general domain and the at least one other domain are configured to have a hierarchical structure, and wherein a sentence is constructed using the at least one domain selected by the user in the selection to exemplify a level of recognizability of the speech according to the at least one domain selected by the user. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A method for speech recognition, comprising:
-
determining a situation of a user; displaying a plurality of domains including a general domain and at least one another domain on a screen that are selectable by the user to identify at least one of plurality of domains as a speech recognition region of a predetermined classification for recognition of a speech, and the displaying displays at least one of the plurality of domains with emphasis when information obtained in relation to the determining of the situation of the user indicates relation to the at least one of the plurality of domains to assist the user in a selection of at least one domain from among the plurality of domains; receiving the selection by the user using at least one of a user input device including at least one of a microphone, a touch screen, a keyboard, and a mouse; and transmitting, with an antenna of a communicator, information regarding the selection by the user of the at least one domain among the plurality of domains, wherein the general domain is associated with a database to be referenced to support the recognition of the speech using all subject matter areas and the at least one other domain being associated with a different database than the database of the general domain to be referenced to support the recognition of the speech using a specific subject matter area, and wherein the general domain and the at least one different domain are configured to have a hierarchical structure, and wherein a sentence is constructed using the at least one domain selected by the user in the selection to exemplify a level of recognizability of the speech according to the at least one domain selected by the user. - View Dependent Claims (12, 13, 14, 15, 16, 17)
-
-
18. A non-transient computer-readable recording medium in which a program executing a method on a computer is stored, the method comprising:
-
determining a situation of a user; displaying a plurality of domains including a general domain and at least one another domain on a screen that are selectable by the user to identify at least one of the plurality of domains as a speech recognition region of a predetermined classification for recognition of a speech, and the displaying displays at least one of the plurality of domains with emphasis when information obtained in relation to the determining of the situation of the user indicates relation to the at least one of the plurality of domains to assist the user in a selection of at least one domain from among the plurality of domains; receiving the selection by the user using at least one of a user input device including at least one of a microphone, a touch screen, a keyboard, and a mouse; and transmitting, with an antenna of a communicator, information regarding the selection by the user of the at least one domain among the plurality of domains, wherein the general domain is associated with a database to be referenced to support the recognition of the speech using all subject matter areas and the at least one other domain being associated with a different database than the database of the general domain to be referenced to support the recognition of the speech using a specific subject matter area, and wherein the general domain and the at least one different domain are configured to have a hierarchical structure, and wherein a sentence is constructed using the at least one domain selected by the user in the selection to exemplify a level of recognizability of the speech according to the at least one domain selected by the user.
-
-
19. An apparatus for speech recognition, comprising:
-
a hardware interface including a screen configured to; display a plurality of domains including a general domain and at least one another domain that are selectable by a user to support recognition of a speech, display at least one of the plurality of domains displayed with emphasis when information obtained in relation to a situation of the user indicates relation to the at least one of the plurality of domains to assist the user in the selection of at least one domain from among the plurality of domains, receive a selection by the user using at least one of a user input device including at least one of a microphone, a touch screen, a keyboard, and a mouse, and transmit information using an antenna regarding the selection by the user; and a speech recognition server configured to refer to data corresponding to the at least one domain selected by the user among reference data for speech recognition through the selection received to perform the recognition of the speech, wherein is associated with a database to be referenced to support the recognition of the speech using all subject matter areas and the at least one other domain being associated with a different database than the database of the general domain to be referenced to support the recognition of the speech using a specific subject matter area, and wherein the general domain and the at least one different domain are configured to have a hierarchical structure, and wherein a sentence is constructed using the at least one domain selected by the user in the selection to exemplify a level of recognizability of the speech according to the at least one domain selected by the user.
-
Specification