Cloning a musical instrument from 16 seconds of audio
In 2020, Magenta released DDSP [1], a machine learning algorithm / python library which made it possible to generate good sounding instrument synthesizers from about 6-10 minutes of data. While working with DDSP for a project, we realised how it was actually quite hard to find 6-10 minute of clean recordings of monophonic instruments. In this project, we have combined the DDSP architecture with a domain adaptation technique from speech synthesis [2]. This domain adaptation technique works by pre-training our model on many different recordings from the Solos dataset [3] first and then…
In plain words
This tool creates playable instrument synthesizers from just 16 seconds of audio recording, using machine learning to clone the sound of monophonic instruments. It combines Google's DDSP algorithm with domain adaptation techniques, requiring far less training data than previous approaches that needed 6-10 minutes of recordings. The tool is designed for musicians and sound designers who want to generate custom instrument models quickly without extensive audio samples.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
In 2020, Magenta released DDSP [1], a machine learning algorithm / python library which made it possible to generate good sounding instrument synthesizers from about 6-10 minutes of data. While working with DDSP for a project, we realised how it was actually quite hard to find 6-10 minute of clean recordings of monophonic instruments. In this project, we have combined the DDSP architecture with a domain adaptation technique from speech synthesis [2]. This domain adaptation technique works by pre-training our model on many different recordings from the Solos dataset [3] first and then fine-tuning parts of the model to the new recording. This allows us to produce decent sounding instrument synthesisers from as little as 16 seconds of target audio instead of 6-10 minutes. [1] https://arxiv.org/abs/2001.04643 [2] https://arxiv.org/abs/1802.06006 [3] https://arxiv.org/abs/2006.07931 We hope to publish a paper on the topic soon.
Does the same job
all alternatives →
- AAAn attempt to rethink a music sequencer design2017 · github.com · ▲305
- FAFree AI-based music demixing in the browser2023 · sevag.xyz · ▲190
Hi all, I've spent some time working on music demixing or music source separation algorithms, which take in a mixed song and output estimates of isolated components (e.g. vocals, drums, bass, other). I took a popular PyTorch model with good performance (Open-Unmix, UMX-L weights), reimplemented the inference steps in C++, and compiled it to WebAssembly for a free client-side music demixer.
- BMBuilding musical synthesizers with SQL queries2023 · github.com · ▲176
If you already know what bytebeat is, you don't need an explanation. If not, check my project :) Here is how it looks: SELECT mono(output( arraySum(x -> 1 / 6 * running_envelope(30 * (1 + x / 6), time, 0.05 * x, 0.005, lfo(0, 0.25, sine_wave, time / 8), 0.1) * sine_wave(time * 80 * exp2(x / 3)), range(12)))) FROM table; To check how it sounds, find the examples in the repository https://github.com/ClickHouse/NoiSQL
- T3TB-303 Synth, Drum Machine and Sequencer in Web Audio2016 · errozero.co.uk · ▲238
- T1TR-101 – A drum synth/sequencer made with Vue and the web audio API2017 · inverted3.gitlab.io · ▲105
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, February 2022
the whole month →
- S2
Life & fun · 2022 · sha256algorithm.com
- E1EdgeDB 1.0▲947
Life & fun · 2022 · edgedb.com
