I'll be attending Interspeech 2025 next week to present our work at Solventum:
"A Hybrid Approach to Combining Role Diarization with ASR for Professional Conversations"
Feel free to drop me a message if you'd like to connect.
My first official milestone as a media composer! My score was selected for a live performance at a film score festival (https://t.co/vF9UFFumJj ). It will be performed by a 16-piece orchestra at a local theater in MN next month. Here is the mockup.
https://t.co/cQUUBgeMry
New music! I covered one of my favorite piano piece by Yiruma, “I” . I also added cello to the piano with cool visualizations :)
https://t.co/5Hug09Wo4F
I started teaching myself orchestral music composition, and will create a series of 1-min music as a milestone along the journey. Here is the first one!
https://t.co/c300aKWOYL
If you are interested in AI and audio, listen to this podcast where I recently got interviewed. I talked about my journey into ML and sound recognition. was a fun experience! https://t.co/j77sd0MDY2
I am presenting my past research works at this meetup tomorrow(12/3, 6:30pm CST). Join remotely if you are interested in sound recognition and ML: https://t.co/IHhFsvofKi
[Postdoc offer] My friends in the @FCIUACh@UAustraldeChile (Valdivia🇨🇱) are looking for a postdoc in Deep Learning for Environmental Sound Classification [remote option]. Details here: https://t.co/UnRoJSeevZ (here a pic of your future workplace😊)Help me w/RT @iambongjun@_LXAI