Adjusting transmit audio at near-end device based on background noise at far-end device
AssigneeMotorola Mobility LLC
InventorsDaniel C. Chisu, Joseph C. Dwyer, Giles T. Davis
Life of this patent
Estimating the term…
Abstract
A voice call is established between two or more computing devices. The voice call may be, for example, audio only or audio and video. One computing device, referred to as a near-end device, receives a digital representation of background noise captured at another computing device, referred to as a far-end device. The near-end device captures voice audio from the user of the near-end device and adjusts the voice audio based at least in part on the digital representation of the background noise at the far-end device. The near-end device then transmits the adjusted voice audio to the far-end device for playback at the far-end device.
Claims20
A method at a near-end device, the method comprising:
- receiving, from a far-end device, a digital representation of a background noise at the far-end device;
- receiving, using a microphone at the near-end device, voice audio from a user of the near-end device, the voice audio including speech and background noise at the near-end device;
- determining a representation of the background noise at the near-end device by filtering the speech from the voice audio from the user of the near-end device;
- adjusting, based at least in part on the digital representation of the background noise at the far-end device, the voice audio for playback at the far-end device by enhancing a characteristic of the speech of the voice audio based on a difference between the background noise at the far-end device and the background noise at the near-end device;
- and
- transmitting, to the far-end device, the adjusted voice audio.
A method at a near-end device, the method comprising:
- capturing, at the near-end device, a background noise signal;
- determining a digital representation of the background noise signal at the near-end device by filtering speech from background noise of the background noise signal;
- transmitting, to a far-end device, the digital representation of the background noise signal;
- receiving, from the far-end device, a digital representation of voice audio generated based at least in part on the digital representation of the background noise signal transmitted to the far-end device;
- generating an output speech signal from the digital representation of the voice audio;
- and
- playing back the output speech signal.
A computing device comprising:
- a processor implemented in hardware;
- a microphone;
- and
- a computer-readable storage media having stored thereon multiple instructions that, responsive to execution by the processor, cause the processor to perform acts including:
- receiving, from a far-end device, a digital representation of a background noise at the far-end device;
- receiving, using the microphone, voice audio from a user of the computing device, the voice audio including speech and background noise at the computing device;
- determining a representation of the background noise at the computing device by filtering the speech from the voice audio from the user of the computing device;
- adjusting, based at least in part on the digital representation of the background noise at the far-end device, the voice audio for playback at the far-end device by enhancing a characteristic of the speech of the voice audio based on a difference between the background noise at the far-end device and the background noise at the computing device;
- and
- transmitting, to the far-end device, the adjusted voice audio.
Dependencies are inferred from the claim text.