公开(公告)号：US11176482B2

公开(公告)日：2021-11-16

申请号：US15571677

申请日：2016-05-04

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Guiping Wang ,  Lie Lu

IPC: G06N20/00 ,  G10L25/51 ,  G06N3/04 ,  G10L25/81

Abstract: Embodiments of training signal processing models for component replacement in signal processing systems are disclosed. A device for training a third signal processing model via a machine learning method include a first calculating unit, a second calculating unit and a training unit. The first calculating unit calculates a first output from each first sample in a first sample set based on a first signal processing model. The second calculating unit calculates a second output from the first sample based on a second signal processing model. The training unit trains a third signal processing model by minimizing a first cost including a first error between the first output and a third output, so that the combination of the second signal processing model and the third signal processing model can simulate the behaviors of the first signal processing model on the first sample set. The third output is an output of the third signal processing model in response to an input including the second output.

公开(公告)号：US11895479B2

公开(公告)日：2024-02-06

申请号：US17637446

申请日：2020-08-19

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Qingyuan Bin ,  Libin Luo ,  Ziyu Yang ,  Zhiwei Shuang ,  Xuemei Yu ,  Guiping Wang

IPC: H04S7/00

CPC classification number: H04S7/30 ,  H04S2420/01

Abstract: A method for steering binauralization of audio is provided. The method comprises steps of: receiving (410) an audio input signal, calculating (430) a confidence value indicating a likelihood that a current audio frame of the audio input signal comprises binauralized audio; determining (450) a state signal based on the confidence value; determining (460) a steering signal, based on the first confidence value, the state signal and an energy value of the audio frame; and generating (470) an audio output signal with steered binauralization by processing the audio input signal according to the steering signal.

公开(公告)号：US20240038258A1

公开(公告)日：2024-02-01

申请号：US18022125

申请日：2021-08-18

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Guiping Wang ,  Lie Lu

IPC: G10L25/81 ,  G10L15/08 ,  G10L15/02

CPC classification number: G10L25/81 ,  G10L15/08 ,  G10L15/02

Abstract: A method of audio content identification includes using a two-stage classifier. The first stage includes previously-existing classifiers and the second stage includes a new classifier. The outputs of the first and second stages calculated over different time periods are combined to generate a steering signal. The final classification results from a combination of the steering signal and the outputs of the first and second stages. In this manner, a new classifier may be added without disrupting existing classifiers.