Image display device for identifying keywords from a voice of a viewer and displaying image and keyword

• US 8,793,129 B2
• Filed: 09/23/2010
• Issued: 07/29/2014
• Est. Priority Date: 09/24/2009
• Status: Active Grant

• Current Assignee: Casio Computer Company Limited
• Original Assignee: Casio Computer Company Limited
• Inventors: Handa, Tetsuya, Mizuno, Kimiyasu, Aibara, Takehiro, Amagai, Hitoshi, Uehara, Naotaka, Kogane, Takayuki, Shinohara, Sumito, Nunokawa, Masato
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US12/888,725
• Publication Number:
  US 20110071832A1
• Time in Patent Office: 1,405 Days
• Field of Search: 704/235, 704/270, 704/272, 704/276, 707/723, 707/748, 382/229, 382/306, 715/201, 715/202
• US Class Current: 704/235
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

It is an object of the present invention to make an act of viewing an image interactive and further enriched. A microphone 18 inputs a voice signal of a voice uttered by a viewer who is viewing a display image displayed on a display portion 17, and causes the voice signal to be stored in a buffer 19. A voice recognition portion 20 identifies at least one word from the voice uttered by the viewer based on the voice signal, and acquires them as a keyword. A counter 21 calculates the number of incidences of the keyword. A display driver 16 causes information including a keyword having a number of incidences that exceeds a threshold value or information derived from the keyword to be displayed together with the display image displayed on the display portion 17.

Claims

1. An image display device comprising:

a voice input portion that inputs a voice signal of a voice uttered by a viewer who is viewing a display image displayed on a display portion;

an acquisition portion that identifies at least one word from the voice uttered by the viewer based on the input voice signal, and acquires the at least one identified word as a first keyword;

a generation portion that, based on both of the first keyword acquired by the acquisition portion and a second keyword included in meta data stored in advance in association with the display image displayed on the display portion, generates a new third keyword that is different from the first keyword and the second keyword; and

a control portion that causes the third keyword generated by the generation portion to be displayed on the display portion together with the display image.

2. An image display device as set forth in claim 1, further comprising a count portion that calculates a number of incidences of the first keyword acquired by the acquisition portion.

3. An image display device as set forth in claim 2, wherein the generation portion generates the new third keyword based on both of (i) a high-incidence first keyword, the high-incidence first keyword being a first keyword of which a number of incidences calculated by the count portion exceeds a threshold, and (ii) the second keyword included in the meta data, the new third keyword being different from the high-incidence first keyword and the second keyword.

4. An image display device as set forth in claim 1, further comprising a detection portion that is configured to detect a face of a person in the display image,

wherein (i) if the detection portion detects a face in the display image, the control portion causes a balloon in which a character string of the third keyword is arranged from a mouth of the detected face to be displayed in the display image, and (ii) if the detection portion does not detect a face in the display image, the control portion causes the third keyword to be displayed in a predetermined region in the display image.

5. An image display device as set forth in claim 3, further comprising a detection portion that is configured to detect a face of a person in the display image,

wherein (i) if the detection portion detects a face in the display image, the control portion causes a balloon in which a character string of the third keyword is arranged from a mouth of the detected face to be displayed in the display image, and (ii) if the detection portion does not detect a face in the display image, the control portion causes the third keyword to be displayed in a predetermined region in the display image.

6. An image display method comprising:

a voice input control step of inputting a voice signal of a voice uttered by a viewer who is viewing a display image displayed on a display portion;

an acquisition step of identifying at least one word from the voice uttered by the viewer based on the input voice signal, and acquiring the at least one identified word as a first keyword;

a generation step of generating, based on both of the first keyword acquired in the acquisition step and a second keyword included in meta data stored in advance in association with the display image displayed on the display portion, a new third keyword that is different from the first keyword and the second keyword; and

a control step of causing the generated third keyword to be displayed on the display portion together with the display image.

7. A non-transitory computer-readable storage medium having a program stored thereon that is executable by a computer that controls an image display device, the program being executable by the computer to implement functions comprising:

a voice input control function that inputs a voice signal of a voice uttered by a viewer who is viewing a display image displayed on a display portion;

an acquisition function that identifies at least one word from the voice uttered by the viewer based on the input voice signal, and acquires the at least one identified word as a first keyword;

a generation function that, based on both of the first keyword by the acquisition function and a second keyword included in meta data stored in advance in association with the display image displayed on the display portion, generates a new third keyword that is different from the first keyword and the second keyword; and

a control function that causes the generated third keyword to be displayed on the display portion together with the display image.