Apparatus, method and program to facilitate retrieval of voice messages

• US 9,824,143 B2
• Filed: 07/02/2012
• Issued: 11/21/2017
• Est. Priority Date: 07/11/2011
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Miyashita, Ken, Hishinuma, Tomohiko, Ohki, Yoshihito, Morimoto, Ryohei, Ono, Junya
• Primary Examiner(s): Klicos, Nicholas
• Application Number:
  US13/539,693
• Publication Number:
  US 20130019176A1
• Time in Patent Office: 1,968 Days
• Field of Search: 715728
• CPC Class Codes: G06F 16/3328 using graphical result space presentation or visualisation
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/221 Announcement of recognition results

Abstract

An information processing apparatus includes a display, an input unit, and a controller. The input unit is configured to receive an input of a first keyword from a user. The controller is configured to retrieve first character information including the input first keyword from a database configured to store a plurality of character information items converted from a plurality of voice information items by voice recognition processing, extract a second keyword that is included in the first character information acquired by the retrieval and is different from the first keyword, and control the display to display a list of items including first identification information with which the acquired first character information is identified and the second keyword included in the first character information.

Claims

1. An information processing apparatus, comprising:

a display;

an input device to receive a first user input of a first keyword inputted by a user in a portion of a graphical user interface; and

a processor configured to;

receive voice call data and store the voice call data in a local memory;

transmit the stored voice call data to a server, wherein the server converts the voice call data to a voice call character string;

cause a first query of the server to be performed using the first keyword of the first user input, wherein the first query retrieves first character information associated with the first keyword, and in response to the first query, cause a first list of data items associated with the first character information to be displayed on the display;

receive a second user input on a data item in the list of data items, wherein the second user input causes the voice call character string to be displayed, wherein the voice call character string includes a second keyword extracted from the voice call character string, and wherein a visual indication of the second keyword is displayed; and

receive a third user input on the voice call character string, and determine a selected position of the third user input on the voice call character string, and

determine whether or not the selected position of the third user input on the voice call character string displayed on the display is of the extracted second keyword, and

(a) when a determination result thereof indicates that the selected position on the voice call character string is one other than that of the second keyword, cause the voice call data to be played from a playback position corresponding to the selected position on the voice call character string displayed on the display, and

(b) when the determination result thereof indicates that the selected position on the voice call character string is that of the second keyword or the visual indication thereof, cause a second query to be performed using the second keyword, wherein the second query retrieves second character information associated with the second keyword from the server without causing the voice call data to be played from the position corresponding to the selected position on the voice call character string displayed on the display, wherein the second character information is used to present a second list of data items associated with the second character information to be displayed on the display.

2. An information processing method for use with a processing apparatus, said method comprising:

receiving a first user input of a first keyword inputted by a user in a portion of a graphical user interface; and

causing, by use of a processor of the processing apparatus,

voice call data of the user to be stored in a local memory,

the stored voice call data of the user to be transmitted to a server, wherein the server converts the voice call data to a voice call character string,

a first query of the server to be performed using the first keyword of the first user input, wherein the first query retrieves first character information associated with the first keyword, and in response to the first query, causing a first list of data items associated with the first character information to be displayed on a display;

a receiving of a second user input on a data item in the list of data items, wherein the second user input causes the voice call character string to be displayed on the display, wherein the voice call character string includes a second keyword extracted from the voice call character string, and wherein a visual indication of the second keyword is displayed on the display; and

a receiving of a third user input on the voice call character string, and a determining of a selected position of the third user input on the voice call character string, and

a determining of whether or not the selected position of the third user input on the voice call character string displayed on the display is of the extracted second keyword, and

(a) when the determining result thereof indicates that the selected position on the voice call character string is one other than that of the second keyword, causing the voice call data to be played from a playback position corresponding to the selected position on the voice call character string displayed on the display, and

(b) when the determining result thereof indicates that the selected position on the voice call character string is that of the second keyword or the visual indication thereof, causing a second query to be performed using the second keyword, wherein the second query retrieves second character information associated with the second keyword from the server without causing the voice call data to be played from the position corresponding to the selected position on the voice call character string displayed on the display, wherein the second character information is used to present a second list of data items associated with the second character information to be displayed on the display.

3. A non-transitory computer readable storage medium having stored thereon a program causing an information processing apparatus to execute the steps of:

receiving a first user input of a first keyword inputted by a user in a portion of a graphical user interface; and

causing, by use of a processor of the information processing apparatus,

voice call data of the user to be stored in a local memory, the stored voice call data of the user to be transmitted to a server, wherein the server converts the voice call data to a voice call character string,

a first query of the server to be performed using the first keyword of the first user input, wherein the first query retrieves first character information associated with the first keyword, and in response to the first query, causing a first list of data items associated with the first character information to be displayed on a display;

a receiving of a second user input on a data item in the list of data items, wherein the second user input causes the voice call character string to be displayed on the display, wherein the voice call character string includes a second keyword extracted from the voice call character string, and wherein a visual indication of the second keyword is displayed on the display; and

a receiving of a third user input on the voice call character string, and a determining of a selected position of the third user input on the voice call character string, and

a determining of whether or not the selected position of the third user input on the voice call character string displayed on the display is of the extracted second keyword, and

(a) when the determining result thereof indicates that the selected position on the voice call character string is one other than that of the second keyword, causing the voice call data to be played from a playback position corresponding to the selected position on the voice call character string displayed on the display, and

(b) when the determination determining result thereof indicates that the selected position on the voice call character string is that of the second keyword or the visual indication thereof, causing a second query to be performed using the second keyword, wherein the second query retrieves second character information associated with the second keyword from the server without causing the voice call data to be played from the position corresponding to the selected position on the voice call character string displayed on the display, wherein the second character information is used to present a second list of data items associated with the second character information to be displayed on the display.