AUDIO CANCELLATION FOR VOICE RECOGNITION

• US 20200135224A1
• Filed: 10/04/2019
• Published: 04/30/2020
• Est. Priority Date: 10/26/2018
• Status: Active Grant

• Current Assignee: Spotify AB (Spotify Technology SA)
• Original Assignee: Spotify AB (Spotify Technology SA)
• Inventors: Bromand, Daniel, Mitic, Richard
• Granted Patent: US 10,943,599 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/0232 Processing in the frequency domain
• CPC Class Codes: G10L 21/0264 characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04M 9/08 Two-way loud-speaking telephone systems with means for conditioning the signal, e.g. for suppressing echoes for one or both directions of traffic
• CPC Class Codes: H04R 2227/003 Digital PA systems using, e.g. LAN or internet
• CPC Class Codes: H04R 2227/005 Audio distribution systems for home, i.e. multi-room use
• CPC Class Codes: H04R 2227/007 Electronic adaptation of audio signals to reverberation of the listening space for PA
• CPC Class Codes: H04R 2227/009 Signal processing in [PA] systems to enhance the speech intelligibility
• CPC Class Codes: H04R 2420/07 Applications of wireless loudspeakers or wireless microphones
• CPC Class Codes: H04R 29/007 for public address systems public address systems per se H04R27/00
• CPC Class Codes: H04R 3/00 Circuits for transducers , loudspeakers or microphones
• CPC Class Codes: H04R 3/04 for correcting frequency response
• CPC Class Codes: H04S 7/305 Electronic adaptation of stereophonic audio signals to reverberation of the listening space H04S7/301 takes precedence
• CPC Class Codes: H04S 7/307 Frequency adjustment, e.g. tone control H04S7/301 takes precedence

Abstract

An audio cancellation system includes a voice enabled computing system that is connected to an audio output device using a wired or wireless communication network. The voice enabled computing device can provide media content to a user and receive a voice command from the user. The connection between the voice enabled computing system and the audio output device introduces a time delay between the media content being generated at the voice enabled computing device and the media content being reproduced at the audio output device. The system operates to determine a calibration value adapted for the voice enabled computing system and the audio output device. The system uses the calibration value to filter the user'"'"'s voice command from a recording of ambient sound including the media content, without requiring significant use of memory and computing resources.

Claims

1. A method of audio cancellation comprising:

generating an audio cue;

playing the audio cue through a sound system in a sound environment, wherein the audio cue is detectable over background noise in the sound environment;

generating a recording of sound using a microphone, the recording of sound including the audio cue;

detecting the audio cue in the recording over the background noise in the sound environment;

determining a time delay between the generation of the audio cue and the time that the audio cue was recorded in the recording; and

using the calibration value to cancel audio from subsequent recordings.

2. The method of claim 1, wherein the audio cue has a first root mean square higher than a second RMS associated with the background noise.

3. The method of claim 1, wherein the audio cue has a strong attack of less than 100 milliseconds.

4. The method of claim 2, wherein the audio cue comprises two or more frequencies.

5. The method of claim 1, wherein the audio cue emanates from a snare drum.

6. The method of claim 2, wherein the background noise is a person talking.

7. The method of claim 2, wherein the background noise is associated with an operation of a motor vehicle or a room or building where the sound system is located.

8. The method of claim 2, wherein the background noise emanates from an engine a home appliance, a television, animal noises, wind noise, or traffic.

9. The method of claim 1, wherein the audio cue comprises a plurality of signals, each signal played at a different time.

10. The method of claim 9, wherein the time that the audio cue is detected in the recording occurs is when a RMS-to-peak ratio reaches or crosses a predetermined threshold.

11. The method of claim 10, wherein the predetermined threshold is 30 dB.

12. The method of claim 11, wherein the audio cue represents two or more signals, and wherein the method further comprises:

averaging the time difference associated with the two or more signals.

13. A media playback system comprising:

a sound system including a media playback device and an audio output device, the media playback device operable to generate a media content signal, and the audio output device configured to play media content using the media content signal; and

wherein the sound system is configured to;

generate an audio cue using the media playback device;

transmit the audio cue to the audio output device;

play the audio cue through the audio output device;

generate a recording of sound using the media playback device, the recording of sound including the audio cue;

detect the audio cue in the recording by determining that a RMS-to-peak ratio of the audio cue reaches or crosses a threshold;

determine a time delay between the generation of the audio cue and the time that the audio cue was recorded in the recording; and

use the calibration value to cancel audio from subsequent recordings.

14. The media playback system of claim 13, wherein the media playback device is paired with the audio output device via a wireless communication network, such as BLUETOOTH®

.

15. The media playback system of claim 13, wherein the sound system is configured to:

generate a second audio cue and playing the second audio cue through the sound system;

generate a recording of sound using the microphone, the recording of sound including the second audio cue;

detect the second audio cue in the recording by determining that a second RMS-to-peak ratio of the second audio cue reaches or crosses the threshold;

determine a second time delay between the generation of the second audio cue and the time that the second audio cue was recorded in the recording;

determine a second calibration value based on the second time delay;

determine a difference between the calibration value and the second calibration value;

determine whether the difference is within a threshold range;

upon determining that the difference is within the threshold range, maintain the first calibration value; and

upon determining that the difference is not within the threshold range, store the second calibration value, and use the second calibration value to cancel audio from subsequent recordings.