Voice tracking apparatus and control method therefor

Patent metadata

Field	Value
Publication number	US-9531948-B2
Application number	US-201314759820-A
Country	US
Kind code	B2
Filing date	Jan 9, 2013
Priority date	Jan 9, 2013
Publication date	Dec 27, 2016
Grant date	Dec 27, 2016

Abstract

A method for controlling a voice tracking apparatus according to an embodiment of the present invention includes the steps of: tracking a sound source of a voice signal generated from the outside; turning an image capturing unit of the voice tracking apparatus toward the location of the tracked sound source; and beamforming the voice signal of the sound source through a voice input unit mounted on the image capturing unit.

First claim

The invention claimed is:

1. A control method of a voice tracking apparatus, the method comprising:
tracking a sound source of a voice signal generated from the outside;
turning an image capturing unit of the voice tracking apparatus toward a location of the tracked sound source, wherein the image capturing unit comprises a second camera including at least one microphone, and the at least one microphone is mounted on one side of the second camera; and
beamforming the voice signal of the sound source through the at least one microphone mounted on the one side of the second camera,
wherein the turning the image capturing unit comprises turning the second camera toward the location of the tracked sound source,
wherein the at least one microphone mounted on the one side of the second camera turns in conjunction with the turning of the second camera, and
wherein the at least one microphone mounted on the one side of the second camera turns toward the tracked sound source if the second camera turns toward the tracked sound source.

2. The control method according to claim 1 , further comprising:
enlargedly capturing an image corresponding to the location of the tracked sound source through the image capturing unit.

3. The control method according to claim 2 , further comprising: checking whether an image of the sound source is an image of a speaker, from the captured image,
wherein the enlargedly capturing of the image corresponding to the location of the tracked sound source comprises enlargedly capturing the image of the speaker when the image of the sound source is the image of the speaker.

4. The control method according to claim 3 , wherein the checking of whether the image of the sound source is the image of the speaker comprises detecting changes in the face and mouth shapes of the speaker from the captured image to check whether the image of the sound source is the image of the speaker.

5. The control method according to claim 1 , wherein the tracking of the sound source comprises tracking the difference of the sound source by using a time difference of arrival (TDOA) technique.

6. The control method according to claim 1 , wherein the beamforming of the voice signal of the sound source comprises beamforming the voice signal of the sound source by using delay and sum beamforming.

7. The control method according to claim 1 , wherein the image capturing unit comprises a first camera and the second camera.

8. A voice tracking apparatus comprising:
an image capturing unit including a second camera;
at least one microphone mounted on one side of the second camera and receiving a voice signal generated from the outside;
a sound source tracking unit tracking a sound source of the received voice signal;
a driving unit turning the image capturing unit toward a location of the tracked sound source; and
a control unit beamforming the voice signal of the tracked sound source through the at least one microphone mounted on the one side of the second camera according to the turning of the image capturing unit,
wherein the driving unit turns the second camera toward the location of the tracked sound source,
wherein the at least one microphone mounted on the one side of the second camera turns in conjunction with the turning of the second camera, and
wherein the at least one microphone mounted on the one side of the second camera turns toward the tracked sound source if the second camera turns toward the tracked sound source.

9. The voice tracking apparatus according to claim 8 , wherein the image capturing unit comprises a first camera and the second camera,
wherein the first camera captures the entire image, and
wherein the second camera enlargedly captures an image corresponding to the location of the tracked sound source of the entire image.

10. The voice tracking apparatus according to claim 9 , further comprising:
an image recognizing unit checking whether an image of the sound source is an image of a speaker, from the captured image.

11. The voice tracking apparatus according to claim 10 , wherein the image recognizing unit detects changes in the face and mouth shapes of the speaker from the captured image to check whether the image of the sound source is the image of the speaker.

12. The voice tracking apparatus according to claim 8 , wherein the driving unit comprises a driving motor.

Assignees

• Lg Electronics Inc

Inventors

• Lee Byounggi
• Jeon Hyejeong
• Lee Heungkyu

Classifications

• G06V40/165 Primary

  using facial parts and geometric relationships · CPC title

• H04N23/62 Primary

  Control of parameters via user interfaces · CPC title

• H04N23/611

  where the recognised objects include parts of the human body · CPC title

• H04N23/61

  based on recognised objects · CPC title

• G10L25/57

  for processing of video signals · CPC title