公开(公告)号：US20220197592A1

公开(公告)日：2022-06-23

申请号：US17601199

申请日：2020-04-03

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Glenn N. DICKINS ,  Feng DENG ,  Michael ECKERT ,  Craig JOHNSTON ,  Paul HOLMBERG

IPC: G06F3/16 ,  H04M3/56 ,  H04L65/403

Abstract: A communication system, method, and computer-readable medium therefor comprise a media server configured to receive a plurality of audio streams from a corresponding plurality of client devices, the media server including circuitry configured to rank the plurality of audio streams based on a predetermined metric, group a first portion of the plurality of audio streams into a first set, the first portion of the plurality of audio streams being the N highest-ranked audio streams, group a second portion of the plurality of audio streams into a second set, the second portion of the plurality of audio streams being the M lowest-ranked audio streams, forward respective audio streams of the first set to a receiver device, and discard respective audio streams of the second set, wherein N and M are independent integers.

公开(公告)号：US20230368807A1

公开(公告)日：2023-11-16

申请号：US18250393

申请日：2021-10-29

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Xiaoyu LIU ,  Michael Getty HORGAN ,  Roy M. FEJGIN ,  Paul HOLMBERG

IPC: G10L21/0232 ,  G10L19/022

CPC classification number: G10L21/0232 ,  G10L19/022

Abstract: A system for suppressing noise and enhancing speech and a related method are disclosed. The system trains a neural network model that takes banded energies corresponding to an original noisy waveform and produces a speech value indicating the amount of speech present in each band at each frame. The neural model comprises a feature extraction block that implements some lookahead. The feature extraction block is followed by an encoder with steady down-sampling along the frequency domain forming a contracting path. The encoder is followed by a corresponding decoder with steady up-sampling along the frequency domain forming an expanding path. The decoder receives scaled output feature maps from the encoder at a corresponding level. The decoder is followed by a classification block that generates a speech value indicating an amount of speech present for each frequency band of the plurality of frequency bands at each frame of the plurality of frames.

公开(公告)号：US20210104254A1

公开(公告)日：2021-04-08

申请号：US17075659

申请日：2020-10-20

Applicant: DOLBY LABORATORIES LICENSING CORPORATION

Inventor： Dong SHI ,  Kai LI ,  Hannes MUESCH ,  David GUNAWAN ,  Paul HOLMBERG ,  Glenn N. DICKINS

IPC: G10L21/0232 ,  H04R3/02 ,  G10L21/0264 ,  H04R3/04

Abstract: Methods for echo estimation or echo management (echo suppression or cancellation) on an input audio signal, with at least one of adaptation of a sparse prediction filter set, modification (for example, truncation) of adapted prediction filter impulse responses, generation of a composite impulse response from adapted prediction filter impulse responses, or use of echo estimation and/or echo management resources in a manner determined at least in part by classification of the input audio signal as being (or not being) echo free. Other aspects are systems configured to perform any embodiment of any of the methods.

公开(公告)号：US20230121651A1

公开(公告)日：2023-04-20

申请号：US18082470

申请日：2022-12-15

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Dong SHI ,  Kai LI ,  Hannes MUESCH ,  David GUNAWAN ,  Paul HOLMBERG ,  Glenn N. DICKINS

IPC: G10L21/0232 ,  H04R3/02 ,  G10L21/0264 ,  H04R3/04

Abstract: Methods for echo estimation or echo management (echo suppression or cancellation) on an input audio signal, with at least one of adaptation of a sparse prediction filter set, modification (for example, truncation) of adapted prediction filter impulse responses, generation of a composite impulse response from adapted prediction filter impulse responses, or use of echo estimation and/or echo management resources in a manner determined at least in part by classification of the input audio signal as being (or not being) echo free. Other aspects are systems configured to perform any embodiment of any of the methods.

公开(公告)号：US20190156852A1

公开(公告)日：2019-05-23

申请号：US16308761

申请日：2017-06-07

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Dong SHI ,  Kai LI ,  Hannes MUESCH ,  David GUNAWAN ,  Paul HOLMBERG ,  Glenn N. DICKINS

IPC: G10L21/0232 ,  G10L21/0264 ,  H04R3/04

Abstract: Methods for echo estimation or echo management (echo suppression or cancellation) on an input audio signal, with at least one of adaptation of a sparse prediction filter set, modification (for example, truncation) of adapted prediction filter impulse responses, generation of a composite impulse response from adapted prediction filter impulse responses, or use of echo estimation and/or echo management resources in a manner determined at least in part by classification of the input audio signal as being (or not being) echo free. Other aspects are systems configured to perform any embodiment of any of the methods.

公开(公告)号：US20180018984A1

公开(公告)日：2018-01-18

申请号：US15648111

申请日：2017-07-12

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Glenn N. DICKINS ,  Paul HOLMBERG ,  Dong SHI

IPC: G10L21/02 ,  H04R29/00 ,  G10L21/0232 ,  G10L21/0216 ,  G10L21/0208

CPC classification number: G10L21/0205 ,  G10L21/0232 ,  G10L25/48 ,  G10L2021/02082 ,  G10L2021/02163 ,  H04R29/00 ,  H04S7/301 ,  H04S7/305

Abstract: Example embodiments disclosed herein relate to assessment and adjustment for an audio environment. A computer-implemented method is provided. The method includes obtaining a first audio signal captured by a device located in an environment. The method also includes analyzing a characteristic of the first audio signal to determine an acoustic performance metric for the environment. The method further includes, in response to the acoustic performance metric being below a threshold, providing a first task for a user to perform based on the characteristic of the first audio signal. The first task is related to an adjustment to a setting of the environment. Embodiments in this regard further provide a corresponding computer program product. Corresponding system and computer program product are also disclosed.