Binaural recording for processing audio signals to enable alerts

Patent metadata

Field	Value
Publication number	US-2016192073-A1
Application number	US-201414583631-A
Country	US
Kind code	A1
Filing date	Dec 27, 2014
Priority date	Dec 27, 2014
Publication date	Jun 30, 2016
Grant date	—

Abstract

A wearable device for binaural audio is described. The wearable device includes a feedback mechanism, a microphone, an always on binaural recorder (AOBR), and a processor. The AOBR is to capture ambient noise via the microphone and interpret the ambient noise. An alert is issued by the processor to the feedback mechanism based on a notification detected via the microphone in the ambient noise.

First claim

What is claimed is:

1 . A wearable device for binaural audio, comprising:
a feedback mechanism; a microphone; an binaural recorder, wherein the binaural recorder is to capture ambient noise via the microphone and interpret the ambient noise; and a processor, wherein an alert is issued to the feedback mechanism based on a notification detected via the microphone in the ambient noise.

2 . The wearable device of claim 1 , wherein the feedback mechanism is a speaker, a vibration source, a heads up display, or any combination thereof.

3 . The wearable device of claim 1 , wherein the alert is a replay of the ambient noise.

4 . The wearable device of claim 1 , wherein the ambient noise is interpreted using a convolutional neural network.

5 . The wearable device of claim 1 , wherein the ambient noise is interpreted using a convolution algorithm.

6 . The wearable device of claim 1 , wherein the captured ambient noise is filtered.

7 . The wearable device of claim 1 , wherein the alert is a sound, vibration, a displayed alert, or any combination thereof.

8 . The wearable device of claim 1 , wherein a location and direction of the notification is determined using sound localization.

9 . The wearable device of claim 1 , wherein the ambient noise is interpreted by comparing a notification detected in the ambient noise to a catalogue of classified sounds.

10 . A method for an always on binaural recording, comprising:
monitoring a background noise; filtering the background noise; interpreting the background noise to determine a notification in the background noise; and issuing an alert based on the notification in the background noise.

11 . The method of claim 10 , wherein the background noise is monitored via an Always On Binaural Recoding.

12 . The method of claim 10 , wherein filtering the background noise is to improve the quality of the monitored background noise.

13 . The method of claim 10 , wherein the notification is interpreted by comparing the notification to a catalogue of classified sounds.

14 . The method of claim 10 , wherein the notification is interpreted by comparing the notification to a catalogue of classified sounds, and the catalogue of classified sounds is tailored for the particular context of use of the wearable device.

15 . The method of claim 10 , wherein the notification is interpreted by comparing the notification to a catalogue of classified sounds, and geo-tagging is used to determine a catalogue of classified sounds.

16 . The method of claim 10 , wherein the alert is issued to the user based on a match between the notification and a catalogue of classified sounds.

17 . A system for binaural audio, comprising:
a display; a speaker; a microphone; a memory that is to store an ambient noise or visual effect, and that is communicatively coupled to the display and the speaker; and a processor communicatively coupled to the radio and the memory, wherein when the processor is to execute the instructions, the processor is to capture and interpret ambient noise and issue an alert via the speaker based on the ambient noise.

18 . The system of claim 17 , wherein a stationary noise reduction is to suppress sources of sustained noise.

19 . The system of claim 17 , wherein a stationary noise reduction is to suppress sources of sustained noise, and emergency notifications are to be excluded from suppression by the stationary noise reduction.

20 . The system of claim 17 , wherein the alert is a replay of the ambient noise.

21 . The system of claim 17 , wherein the alert is prioritized and delivered to a user based on priority.

22 . The system of claim 17 , wherein the alert is prioritized and delivered to a user based on a user configuration

23 . The system of claim 17 , wherein interpreting includes convolution.

24 . The system of claim 17 , wherein the alert is interpreted using a convolutional neural network.

25 . The system of claim 17 , wherein the processor filters the ambient noise to produce an audio sample.

Assignees

• Intel Corp

Inventors

• Poornachandran Rajesh
• Gottardo David
• Kar Swarnendu
• Dadu Saurabh
• Macdonald Mark

Classifications

• G10L25/51 Primary

  for comparison or discrimination · CPC title

• H04R5/04 Primary

  Circuit arrangements, {e.g. for selective connection of amplifier inputs/outputs to loudspeakers, for loudspeaker detection, or for adaptation of settings to personal preferences or hearing impairments (combinations of amplifiers H03F3/68; stereophonic systems H04S)} · CPC title

• G10L25/30

  using neural networks · CPC title

• H04S7/40

  Visual indication of stereophonic sound image · CPC title

• H04R3/005

  for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407) · CPC title