Search

Jason Wung

from Santa Clara, CA
Age ~42
Get Report
Also known as:
Jason Wang
Related to:
Qiyuan Fu, 69Karl Alan Lindor, 62Chengyu WangWang Kangran, 34Jody Wung, 31Chong G Wang, 37Chien L Wung, 71Mingfan Wung, 69Xiaochun WangJoanna Wung, 40
Connected to:
Christopher H Wunker, 54Ricard S Wunn, 74Eric Wunnenberg, 62Jessica L Wunner, 42Joellen L Wunner, 39Douglas V Wunrow, 73Steven H Wunrow, 70Alyssa E Wunsch, 33Barbara J Wunsch, 59Catherine M Wunsch, 94

Jason Wung Phones & Addresses

  • Santa Clara, CA
  • Los Angeles, CA
  • Benicia, CA
  • Atlanta, GA
  • Bothell, WA

Resumes

Resumes

Jason Wung Photo 1

Dsp Research Engineer

View page
Location:
3879 Melody Ln, Santa Clara, CA 95051
Industry:
Consumer Electronics
Work:
Beats By Dr. Dre May 2013 - Aug 2014
Direct Support Professional Research Engineer
Apple May 2013 - Aug 2014
Dsp Research Engineer
Georgia Institute of Technology May 2008 - May 2013
Graduate Research Assistant
Microsoft May 2012 - Aug 2012
Research Intern
Georgia Institute of Technology Aug 2007 - May 2008
Graduate Teaching Assistant
Education:
Georgia Tech 2013
Doctorates, Doctor of Philosophy, Computer Engineering Georgia Tech 2010
Master of Science, Masters, Computer Engineering National Taiwan University 2004
National Taiwan University
Georgia Institute of Technology
Doctorates, Doctor of Philosophy, Computer Engineering, Philosophy
Skills:
Matlab
Verilog
Latex
Signal Processing
Machine Learning
Languages:
English
Mandarin
Jason Wung Photo 2

Jason Wung

View page

Publications

Us Patents

Spatially Informed Acoustic Echo Cancelation

View page
US Patent:
20220369030, Nov 17, 2022
Filed:
May 17, 2021
Appl. No.:
17/322539
Inventors:
- Cupertino CA, US
Jason Wung - Santa Clara CA, US
Ante Jukic - Culver City CA, US
Ramin Pishehvar - La Crescenta CA, US
Joshua D. Atkins - Los Angeles CA, US
International Classification:
H04R 3/04
H04R 3/00
H04R 5/04
G10L 21/0216
G10L 25/78
Abstract:
A plurality of microphone signals can be captured with a plurality of microphones of the device. One or more echo dominant audio signals can be determined based on a pick-up beam directed towards one or more speakers of a playback device. Sound that is emitted from the one or more speakers and sensed by the plurality of microphones can be removed from plurality of microphone signals, by using the one or more echo dominant audio signals as a reference, resulting in clean audio.

End-To-End Time-Domain Multitask Learning For Ml-Based Speech Enhancement

View page
US Patent:
20220366927, Nov 17, 2022
Filed:
May 15, 2021
Appl. No.:
17/321411
Inventors:
- Cupertino CA, US
Ante Jukic - Los Angeles CA, US
Mehrez Souden - Los Angeles CA, US
Jason Wung - Santa Clara CA, US
Feipeng Li - Sunnyvale CA, US
Joshua D. Atkins - Los Angeles CA, US
International Classification:
G10L 21/0216
G10L 15/16
G06N 20/00
Abstract:
Disclosed is a multi-task machine learning model such as a time-domain deep neural network (DNN) that jointly generate an enhanced target speech signal and target audio parameters from a mixed signal of target speech and interference signal. The DNN may encode the mixed signal, determine masks used to jointly estimate the target signal and the target audio parameters based on the encoded mixed signal, apply the mask to separate the target speech from the interference signal to jointly estimate the target signal and the target audio parameters, and decode the masked features to enhance the target speech signal and to estimate the target audio parameters. The target audio parameters may include a voice activity detection (VAD) flag of the target speech. The DNN may leverage multi-channel audio signal and multi-modal signals such as video signals of the target speaker to improve the robustness of the enhanced target speech signal.

Spatially Informed Audio Signal Processing For User Speech

View page
US Patent:
20210074316, Mar 11, 2021
Filed:
Dec 9, 2019
Appl. No.:
16/708296
Inventors:
- Cupertino CA, US
Ante JUKIC - Los Angeles CA, US
Jason WUNG - Cupertino CA, US
Ashrith DESHPANDE - San Jose CA, US
Joshua D. ATKINS - Los Angeles CA, US
International Classification:
G10L 25/81
G10L 25/18
G10L 21/0232
G06K 9/00
G10L 15/25
G10L 15/22
G06N 7/00
G06N 20/00
Abstract:
A device implementing a system for processing speech in an audio signal includes at least one processor configured to receive an audio signal corresponding to at least one microphone of a device, and to determine, using a first model, a first probability that a speech source is present in the audio signal. The at least one processor is further configured to determine, using a second model, a second probability that an estimated location of a source of the audio signal corresponds to an expected position of a user of the device, and to determine a likelihood that the audio signal corresponds to the user of the device based on the first and second probabilities.

Voice Quality Enhancement Techniques, Speech Recognition Techniques, And Related Systems

View page
US Patent:
20150112672, Apr 23, 2015
Filed:
Oct 17, 2014
Appl. No.:
14/517700
Inventors:
- Cupertino CA, US
Jason Wung - Los Angeles CA, US
Joshua Atkins - Pacific Palisades CA, US
Raghavendra Prabhu - Redondo Beach CA, US
International Classification:
G10L 21/0208
G10L 15/20
US Classification:
704233
Abstract:
An echo canceller can be arranged to receive an input signal and to receive a reference signal. The echo canceller can subtract a linear component of the reference signal from the input signal. A noise suppressor can suppress non-linear effects of the reference signal in the input signal in correspondence with a large number of selectable parameters. Such suppression can be provided on a frequency-by-frequency basis, with a unique set of tunable parameters selected for each frequency. A degree of suppression provided by the noise suppressor can correspond to an estimate of residual echo remaining after the one or more linear components of the reference signal have been subtracted from the input signal, to an estimated double-talk probability, and to an estimated signal-to-noise ratio of near-end speech in the input signal for each respective frequency. A speech recognizer can receive a processed input signal from the noise suppressor.
Control profile
Jason Wung from Santa Clara, CA, age ~42 Get Report