Profile banner
Karn Watcharasupat

Karn Watcharasupat

PhD candidate, Music Technology; Audio ML/AI/DSP Researcher

Atlanta, Georgia, US
Joined July 2026

Network

1.8K connections

Summary

Karn is an accomplished academic in Music Technology, currently pursuing a PhD at Georgia Institute of Technology in the Music Informatics Group. Her research is centered on audio source separation, specifically developing algorithms to isolate individual instruments from complex audio mixes with flexibility and precision. gatech+3
She has a strong background in electrical and electronic engineering from Nanyang Technological University, graduating with highest honors and receiving the Lee Kuan Yew Gold Medal. This engineering foundation supports her interdisciplinary work in audio machine learning, AI, and digital signal processing. orcid+1
Karn has gained valuable industry experience through internships at top technology companies like Netflix and Apple, applying her audio separation research to real-world applications in film production and inclusive audio technologies. gatech+1
Her exceptional academic and research contributions have been recognized with prestigious awards such as the Google Ph.D. Fellowship in Machine Perception, the IEEE Signal Processing Society Scholarship, and the AAUW International Doctoral Degree Fellowship. gatech+2
Karn is a prolific researcher with over 20 peer-reviewed works and a co-inventor of a granted patent in asynchronous array source separation, demonstrating her significant impact on the fields of music information retrieval, machine learning, and audio signal processing. google+1

Work

Education

Writing

Soundscape descriptors in eighteen languages: Translation and validation through listening experiments

January 1, 2024
Favicon imagescholar.google.com

ARAUS: A large-scale dataset and baseline models of affective responses to augmented urban soundscapes

January 1, 2023
Favicon imagescholar.google.com

Preliminary results of the Soundscape Attributes Translation Project (SATP): Lessons Learned and Next Steps

January 1, 2023
Favicon imagescholar.google.com

FRCRN: Boosting feature representation using frequency recurrence for monaural speech enhancement

January 1, 2022
Favicon imagescholar.google.com

Quantitative evaluation approach for translation of perceptual soundscape attributes: Initial application to the Thai Language

January 1, 2022

Examines a quantitative evaluation method based on the circumplex model of soundscape perception to assess overall translation quality of soundscape attributes from English to Thai.

Favicon imagescholar.google.com

Crossing the linguistic causeway: A binational approach for translating soundscape attributes to Bahasa Melayu

January 1, 2022
Favicon imagescholar.google.com

Probably Pleasant? A Neural-Probabilistic Approach to Automatic Masker Selection for Urban Soundscape Augmentation

January 1, 2022
Favicon imagescholar.google.com

SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection

January 1, 2021
Favicon imagescholar.google.com

SALSA-Lite: A Fast and Effective Feature for Polyphonic Sound Event Localization and Detection with Microphone Arrays

January 1, 2021
Favicon imagescholar.google.com

DCASE 2021 Task 3: Spectrotemporally-aligned Features for Polyphonic Sound Event Localization and Detection

January 1, 2021
Favicon imagescholar.google.com

Hobbies

Karn was a 'band kid' in high school, deeply involved in band programs and developed a love for music and mathematics. gatech