Device and method for selective image display in response to detected voice characteristics

• US 8,311,839 B2
• Filed: 05/09/2010
• Issued: 11/13/2012
• Est. Priority Date: 04/02/2010
• Status: Active Grant

• Current Assignee: Transcend Information Incorporated
• Original Assignee: Transcend Information Incorporated
• Inventors: Chao, Li-Jen, Tzou, Din-Ji, Chiu, Chih-Heng, Shu, Chung-Won, Chen, Kuan-Jen
• Primary Examiner(s): Pullias, Jesse
• Application Number:
  US12/776,424
• Publication Number:
  US 20110246204A1
• Time in Patent Office: 919 Days
• Field of Search: 704/270, 704/272, 704/275, 704/276, 704/246, 704/E17.002, 704/E17.005
• US Class Current: 704/275
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

An image display device includes a display unit, a storage unit, a voice receiving unit and a processing unit. The storage unit stores a plurality of image data, a plurality of voice data and a plurality of image files, wherein each of the image data is corresponding to one of the voice data respectively. The voice receiving unit receives a current voice. The processing unit judges whether the current voice is similar to one of the voice data, so as to determine one image data corresponding to the current voice. When the current voice is similar to one of the voice data, the processing unit determines whether each of the image files contains the image data corresponding to the current voice and then displays the image file(s), which contain the image data corresponding to the current voice, on the display unit.

Claims

1. An image display device comprising:

a display unit;

a storage unit for storing a plurality of image data converted from a plurality of head portrait data of persons, a plurality of voice data converted from a plurality of voiceprint data of persons, and a plurality of image files, wherein each of the image data is corresponding to one of the voice data respectively, and each of the image files is able to contain at least one of the image data;

a voice receiving unit for receiving a current voice; and

a processing unit electrically connected to the display unit, the storage unit and the voice receiving unit, the processing unit judging whether the current voice is similar to one of the voice data, so as to determine the image data corresponding to the current voice, when the current voice is similar to one of the voice data, the processing unit judging whether each of the image files contains the image data corresponding to the current voice and then displaying the image file(s), which contain the image data corresponding to the current voice, on the display unit.

2. The image display device of claim 1, wherein the processing unit further comprises image and voice recognition technology to convert the plurality of head portrait data of persons and the voiceprint data of persons into the plurality of image data and the plurality of voice data.

3. An image display method comprising steps of:

converting a plurality of head portrait data of persons into a plurality of image data;

converting a plurality of voiceprint data of persons into a plurality of voice data, wherein each of the image data is corresponding to one of the voice data respectively;

storing the plurality of image data and the plurality of voice data in a storage unit;

storing a plurality of image files in the storage unit, wherein each of the plurality of image files is able to contain at least one of the plurality of image data;

receiving a current voice;

judging whether the current voice is similar to one of the voice data by voice recognition technology, so as to determine the image data corresponding to the current voice;

when the current voice is similar to one of the voice data, judging whether each of the image files contains the image data corresponding to the current voice by image recognition technology; and

displaying the image file(s) containing the image data corresponding to the current voice.

6. The image display method of claim 3, wherein the voice characteristic is selected from a group consisting of sex, age, language, surrounding sound and specific human voice.

4. An image display method comprising steps of:

storing a plurality of image data and a plurality of voice data in a storage unit, wherein each of the image data is corresponding to one of the voice data respectively;

storing a plurality of image files in the storage unit;

classifying the image files into a plurality of display groups by judging whether each of the image files contains at least one of the image data by image recognition technology, wherein each of the display groups is corresponding to one of the image data;

receiving a current voice;

judging whether the current voice is similar to one of the voice data by voice recognition technology, so as to determine the image data and the display group corresponding to the current voice

displaying the image files of the determined display group corresponding to the current voice.

5. An image display method comprising steps of:

storing a plurality of image files in a storage unit;

classifying the plurality of image files into a plurality of display groups according to a plurality of voice characteristics by using image recognition technology, such that each of the plurality of display groups comprises classified image files;

setting one of the plurality of voice characteristics for displaying;

receiving a current voice;

judging the set voice characteristic of the current voice by voice recognition technology;

determining one of the plurality of display groups corresponding to the current voice according to the judging result; and

displaying the image files classified in the determined display group.