Remote conferencing center

• US 8,560,309 B2
• Filed: 12/29/2009
• Issued: 10/15/2013
• Est. Priority Date: 12/29/2009
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Pance, Aleksandar, King, Nicholas Vincent
• Primary Examiner(s): JACKSON, JAKIEDA R
• Application Number:
  US12/649,025
• Publication Number:
  US 20110161074A1
• Time in Patent Office: 1,386 Days
• Field of Search: 704/231
• US Class Current: 704/231
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 21/028 using properties of sound source
• CPC Class Codes: G11B 20/10527 Audio or video recording; Data buffering arrangements G11B20/12 - G11B20/18 take precedence
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

Certain embodiments disclosed herein relate to systems and methods for recording audio and video. In particular, in one embodiment, a method of recording audio signals is provided. The method includes recording audio signals with a plurality of distributed audio transducers to create multiple recordings of the audio signals and providing each of the multiple recordings of the audio signals to a computing device. The computing device combines each of the multiple recordings into a master recording and determines a source for each audio signal in the master recording. Additionally, the computing device stores each audio signal in separate audio files according to the determined source of each audio signal.

Claims

1. A method of recording audio signals comprising:

recording audio signals with a plurality of distributed audio transducers to create multiple recordings of the audio signals;

providing each of the multiple recordings of the audio signals to a computing device, the computing device;

combining each of the multiple recordings into a master recording;

determining, from the master recording, a plurality of sources of distinct audio signals in the master recording, each determined source of the plurality of sources comprising a entity that produces sound; and

storing, for each of one or more of the determined plurality of sources, a corresponding audio signal in a separate audio file distinct from each of the multiple recordings.

2. The method of claim 1 wherein the operation of combining each of the multiple recordings into a master recording comprises:

aligning spectral distributions of the multiple recordings so that each recording coincides time-wise with the other recordings; and

selecting a highest amplitude signal for each of a plurality of time-steps for use in the master recording.

3. The method of claim 1, further comprising:

obtaining an audio sample from each of a plurality of sources of audio signals; and

comparing each of the multiple recordings with the recorded audio samples to determine the sources of the multiple recordings.

4. The method of claim 1 wherein determining a plurality of sources of distinct audio signals in the master recording comprises:

determining an origin of a respective audio signal relative to the plurality of distributed transducers by comparing at least one of an amplitude and a phase difference between the audio signals received at more than one audio transducer.

5. The method of claim 1, further comprising:

transmitting the recorded audio signals from a plurality of electronic devices to the computing device for creation of the master recording; and

transmitting the master recording to one or more of the electronic devices in the plurality of electronic devices;

wherein

the plurality of distributed audio transducers are each part of a distinct electronic device in the plurality of electronic devices.

6. The method of claim 5 wherein transmitting the recorded audio signals comprises transmitting the audio signals via a network connection.

7. The method of claim 5 wherein transmitting the recorded audio signals comprises transmitting the audio signals directly to the computing device via a short range RF transmission.

8. The method of claim 1 further comprising:

transcribing the master recording; and

inserting source information to identify sources in the transcription.

9. The method of claim 5 wherein the multiple audio recordings are transmitted at the end of a recording session.

10. A method of managing audio signals from multiple sources comprising:

electronically receiving a plurality of audio signals from a plurality of electronic devices;

based on at least one characteristic of the plurality of audio signals, electronically determining, from the plurality of audio signals, identities of a plurality of sources of distinct audio signals, each identified source of the plurality of sources comprising a entity that produces sound; and

sorting the plurality of audio signals according to the determined identities; and

storing audio signals corresponding to two or more of the identified sources in separate audio files according to the sorting.

11. The method of claim 10 wherein determining, from the plurality of audio signals, identities of a plurality of sources of distinct audio signals comprises:

comparing each of the plurality of audio signals with at least one sample audio signal to find coincident speech patterns.

12. The method of claim 10 wherein determining, from the plurality of audio signals, identities of a plurality of sources of distinct audio signals comprises:

storing an unidentified recorded audio signal;

labeling the stored unidentified recorded audio signal;

subsequently comparing each of the plurality of audio signals with at least one characteristic of the unidentified recorded audio signal; and

labeling at least one of the plurality of audio signals with the same label as the unidentified recorded signal if a factor of the at least one of the plurality of audio signals patterns matches the characteristic of the unidentified audio signal;

wherein the characteristic relates to speech.

13. The method of claim 10, further comprising discretely retrieving the recorded audio signals according to the determined identities.

14. The method of claim 10, further comprising:

retrieving each of the separately stored audio files; and

organizing the separately stored audio files for playback according to a time stamp on the audio files.

15. An audio recording system comprising:

a plurality of distributed sound transducers;

memory;

one or more processors; and

one or more programs stored in memory and configured for execution by the one or more processors, the one or more programs including;

instructions to record audio signals with the plurality of distributed audio transducers to create multiple recordings of the audio signals;

instructions to combine each of the multiple recordings into a master recording;

instructions to determine, from the master recording, a plurality of sources of distinct audio signals in the master recording, each determined source of the plurality of sources comprising a entity that produces sound; and

instructions to store, for each of one or more of the determined plurality of sources, a corresponding audio signal in a separate audio file distinct from each of the multiple recordings.

16. The audio recording system of claim 15 further comprising one or more cameras configured to capture images of the sources for the received audio signals.

17. The audio recording system of claim 16, the one or more programs further including instructions to determine the location of each of one or more respective sources in the plurality of sources of distinct audio signals relative to the plurality of distributed sound transducers;

and

wherein the one or more cameras are configured to move to be directed towards at least one of the one or more determined locations.

18. The audio recording system of claim 15 further comprising at least one antenna, the antenna being configured to receive audio signals transmitted from the plurality of distributed sound transducers.

19. The audio recording system of claim 15, wherein the instructions to determine, from the master recording, a plurality of sources of distinct audio signals in the master recording include instructions to execute voice recognition software.

20. The audio recording system of claim 15 further comprising a speaker for playback of the audio signals, wherein the stored audio signals are retrieved and combined for playback according to a time stamp associated with the stored audio signals.