About

 

I am an audio enthusiast who loves exploring the world of sound. Ever wondered how noise-cancelling headphones block sounds, how your voice stays clear on calls, or what happens when you adjust an equalizer? Say hello to the fascinating world of Digital Signal Processing (DSP).

 

For the past decade I've been involved in the research and development of DSP algorithms for speech feature extraction, processing and enhancement. Since 2019 I work at Analog Devices Inc. in Leuven, Belgium where I develop voice processing algorithms for some of the world's most popular TWS earbuds, Headsets (+VR), Smartwatches and PSAP devices. During this time, I also co-invented 4 U.S. Patents on Audio DSP Systems and Methods.

 

Previously I spent 2 years as an Audio DSP Researcher at Cirrus Logic in Melbourne, Australia, working on speech enhancement using IMUs and improving voice biometrics for some of the world's most popular headsets and smartphones.

 

I hold a Bachelor's in Mechatronics Engineering (UOM) and a Master's in Electrical and Electronic Engineering (RMIT), with a thesis focused on extracting and analyzing speech acoustic parameters for early signs of depression in adolescents. Post-graduation, I received a grant from the Defence Science Institute of Australia (DSI) to continue as a Research Assistant at RMIT, contributing to the development of the Mental State Tracker for real-time emotion recognition from speech.

 

 

 

 

Research

 

I specialize in developing and optimizing frequency-domain algorithms for applications like speech enhancement, multi-mic voice calling, and bone conduction sensor processing. My expertise spans dynamic range control (compressors, expanders, noise gates, limiters), pitch detection and processing, acoustic echo cancellation, noise suppression, and parametric equalization. I also work on advanced techniques such as beamforming, acoustic feature extraction and hearing augmentation with a focus on objective speech metrics.

 

 

 

 

Patents & Publication

 

MAY. 2024 – U.S. Patent, US11984107B2 | View | PDF |
Audio signal processing method and system for echo suppression using an MMSE-LSA estimator.

 

MAY. 2024 – U.S. Patent, US11978468B2 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by a bone conduction, feedback and feedforward sensor.

 

JUN. 2022 – U.S. Patent, US20230419981A1 | View | PDF |
Audio signal processing method and system for correcting a spectral shape of a voice signal measured by sensor. (Pending)

 

FEB. 2022 – U.S. Patent, US20230253002A1 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by air and bone conduction sensors. (Pending)

 

DEC. 2015 – IEEE Paper, 9th ICSPCS (Cairns, Australia) | View |
Statistical differences in speech acoustics of major depressed and non-depressed adolescents.

About

 

I am an audio enthusiast who loves exploring the world of sound. Ever wondered how noise-cancelling headphones block sounds, how your voice stays clear on calls, or what happens when you adjust an equalizer? Say hello to the fascinating world of Digital Signal Processing (DSP).

 

For the past decade I've been involved in the research and development of DSP algorithms for speech feature extraction, processing and enhancement. Since 2019 I work at Analog Devices Inc. in Leuven, Belgium where I develop voice processing algorithms for some of the world's most popular TWS earbuds, Headsets (+VR), Smartwatches and PSAP devices. During this time, I also co-invented 4 U.S. Patents on Audio DSP Systems and Methods.

 

Previously I spent 2 years as an Audio DSP Researcher at Cirrus Logic in Melbourne, Australia, working on speech enhancement using IMUs and improving voice biometrics for some of the world's most popular headsets and smartphones.

 

I hold a Bachelor's in Mechatronics Engineering (UOM) and a Master's in Electrical and Electronic Engineering (RMIT), with a thesis focused on extracting and analyzing speech acoustic parameters for early signs of depression in adolescents. Post-graduation, I received a grant from the Defence Science Institute of Australia (DSI) to continue as a Research Assistant at RMIT, contributing to the development of the Mental State Tracker for real-time emotion recognition from speech.

 

 

 

Research

 

I specialize in developing and optimizing frequency-domain algorithms for applications like speech enhancement, multi-mic voice calling, and bone conduction sensor processing. My expertise spans dynamic range control (compressors, expanders, noise gates, limiters), pitch detection and processing, acoustic echo cancellation, noise suppression, and parametric equalization. I also work on advanced techniques such as beamforming, acoustic feature extraction, hearing augmentation, and headset characterization, with a focus on objective speech metrics.

 

 

 

Patents & Publication

 

MAY. 2024 – U.S. Patent, US11984107B2 | View | PDF |
Audio signal processing method and system for echo suppression using an MMSE-LSA estimator.

 

MAY. 2024 – U.S. Patent, US11978468B2 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by a bone conduction, feedback and feedforward sensor.

 

JUN. 2022 – U.S. Patent, US20230419981A1 | View | PDF |
Audio signal processing method and system for correcting a spectral shape of a voice signal measured by sensor. (Pending)

 

FEB. 2022 – U.S. Patent, US20230253002A1 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by air and bone conduction sensors. (Pending)

 

DEC. 2015 – IEEE Paper, 9th ICSPCS (Cairns, Australia) | View |
Statistical differences in speech acoustics of major depressed and non-depressed adolescents.

About

 

I am an audio enthusiast who loves exploring the world of sound. Ever wondered how noise-cancelling headphones block sounds, how your voice stays clear on calls, or what happens when you adjust an equalizer? Say hello to the fascinating world of Digital Signal Processing (DSP).

 

For the past decade I've been involved in the research and development of DSP algorithms for speech feature extraction, processing and enhancement. Since 2019 I work at Analog Devices Inc. in Leuven, Belgium where I develop voice processing algorithms for some of the world's most popular TWS earbuds, Headsets (+VR), Smartwatches and PSAP devices. During this time, I also co-invented 4 U.S. Patents on Audio DSP Systems and Methods.

 

Previously I spent 2 years as an Audio DSP Researcher at Cirrus Logic in Melbourne, Australia, working on speech enhancement using IMUs and improving voice biometrics for some of the world's most popular headsets and smartphones.

 

I hold a Bachelor's in Mechatronics Engineering (UOM) and a Master's in Electrical and Electronic Engineering (RMIT), with a thesis focused on extracting and analyzing speech acoustic parameters for early signs of depression in adolescents. Post-graduation, I received a grant from the Defence Science Institute of Australia (DSI) to continue as a Research Assistant at RMIT, contributing to the development of the Mental State Tracker for real-time emotion recognition from speech.

 

 

 

Research

 

I specialize in developing and optimizing frequency-domain algorithms for applications like speech enhancement, multi-mic voice calling, and bone conduction sensor processing. My expertise spans dynamic range control (compressors, expanders, noise gates, limiters), pitch detection and processing, acoustic echo cancellation, noise suppression, and parametric equalization. I also work on advanced techniques such as beamforming, acoustic feature extraction, hearing augmentation, and headset characterization, with a focus on objective speech metrics.

 

 

 

Patents & Publication

 

MAY. 2024 – U.S. Patent, US11984107B2 | View | PDF |
Audio signal processing method and system for echo suppression using an MMSE-LSA estimator.

 

MAY. 2024 – U.S. Patent, US11978468B2 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by a bone conduction, feedback and feedforward sensor.

 

JUN. 2022 – U.S. Patent, US20230419981A1 | View | PDF |
Audio signal processing method and system for correcting a spectral shape of a voice signal measured by sensor. (Pending)

 

FEB. 2022 – U.S. Patent, US20230253002A1 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by air and bone conduction sensors. (Pending)

 

DEC. 2015 – IEEE Paper, 9th ICSPCS (Cairns, Australia) | View |
Statistical differences in speech acoustics of major depressed and non-depressed adolescents.

About

 

I am an audio enthusiast who loves exploring the world of sound. Ever wondered how noise-cancelling headphones block sounds, how your voice stays clear on calls, or what happens when you adjust an equalizer? Say hello to the fascinating world of Digital Signal Processing (DSP).

 

For the past decade I've been involved in the research and development of DSP algorithms for speech feature extraction, processing and enhancement. Since 2019 I work at Analog Devices Inc. in Leuven, Belgium where I develop voice processing algorithms for some of the world's most popular TWS earbuds, Headsets (+VR), Smartwatches and PSAP devices. During this time, I also co-invented 4 U.S. Patents on Audio DSP Systems and Methods.

 

Previously I spent 2 years as an Audio DSP Researcher at Cirrus Logic in Melbourne, Australia, working on speech enhancement using IMUs and improving voice biometrics for some of the world's most popular headsets and smartphones.

 

I hold a Bachelor's in Mechatronics Engineering (UOM) and a Master's in Electrical and Electronic Engineering (RMIT), with a thesis focused on extracting and analyzing speech acoustic parameters for early signs of depression in adolescents. Post-graduation, I received a grant from the Defence Science Institute of Australia (DSI) to continue as a Research Assistant at RMIT, contributing to the development of the Mental State Tracker for real-time emotion recognition from speech.

 

 

Research

 

I specialize in developing and optimizing frequency-domain algorithms for applications like speech enhancement, multi-mic voice calling, and bone conduction sensor processing. My expertise spans dynamic range control (compressors, expanders, noise gates, limiters), pitch detection and processing, acoustic echo cancellation, noise suppression, and parametric equalization. I also work on advanced techniques such as beamforming, acoustic feature extraction, hearing augmentation, and headset characterization, with a focus on objective speech metrics.

 

 

Patents & Publication

 

MAY. 2024 – U.S. Patent, US11984107B2 | View | PDF |
Audio signal processing method and system for echo suppression using an MMSE-LSA estimator.

 

MAY. 2024 – U.S. Patent, US11978468B2 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by a bone conduction, feedback and feedforward sensor.

 

JUN. 2022 – U.S. Patent, US20230419981A1 | View | PDF |
Audio signal processing method and system for correcting a spectral shape of a voice signal measured by sensor. (Pending)

 

FEB. 2022 – U.S. Patent, US20230253002A1 | View | PDF |
Audio signal processing method and system for noise mitigation of a voice signal measured by air and bone conduction sensors. (Pending)

 

DEC. 2015 – IEEE Conference Paper, 9th ICSPCS (Cairns, Australia) | View |
Statistical differences in speech acoustics of major depressed and non-depressed adolescents.