About Me

Hi there! My name is Hao Hao Tan (郑豪好), or you can call me Harry. I am from Kuala Lumpur, Malaysia, and currently residing in Singapore.

I’m currently at BandLab Technologies, applying AI/ML to assist and enhance music creation workflow. Some examples include SongStarter, Audio-to-MIDI, Smart MIDI Tools, Voice Changer, Splitter, and others. I work with a broad range of MIR topics, and I recently also focus more on ML engineering topics like on-device model serving and optimization.

My experience revolves around technology that empowers creative applications, mostly in music. Before BandLab, I was at TikTok working on the deep ranking module of TikTok’s main feed recommendation. I also worked at a music tech startup called Fairphonic, where I helped build a deep-learning based music content recognition engine that can identify both originals and covers to fix music royalties attribution. My first internship was at PayPal, but I might have chosen multimedia over payments for the next few years.

I also work on independent research / open-source projects, such as:

• Syntheon, a parameter inference model for synths;
• frechet-audio-distance, a lightweight library for Frechet Audio Distance calculation.
• A PyTorch implementation of differentiable wavetable synthesis.

I am a classically trained pianist, sometimes I make weird electronic beats. I grew up listening Hong Kong Cantonese classics, learnt about English pop hits and IU during school. Now I like pure instrumental or electronic stuffs - Rush Garcia, TheFatRat, Vicetone, Glacier, Avenza, 裁缝铺, and recently Drics. Probably Paramore and Imagine Dragons would be two of the biggest exceptions.

Please feel free reach me at helloharry66 [at] gmail or @GoodGood014 on Twitter.