HANCE 2.0: Realtime Stem Separation - Hello, Music Industry

1 min read
HANCE 2.0: Realtime Stem Separation - Hello, Music Industry

HANCE Audio Engine v2.0.1 is now live - and with it, realtime stem separation made effortless.

Songs are a composition of sounds mixed together. For simplicity’s sake, say: vocals, piano and drums. The music industry usually calls these categories different stems. Once recorded, mixing these sounds into one song and one file is rather simple. Separating them on the other hand - has been a different story… until now.

Stem separation is like making music in reverse. Instead of creating a composition of sounds, vocals and instruments - you tear them apart. Not with brute force, but surgically, to preserve the remaining organs. Pun intended.

HANCE 2.0 includes:

  • Stem separation: Models for vocals, piano, bass and drums
  • Parameter support: Possibility to set maximum attenuation, sensitivity, etc.
  • XcFramework: Simplifies development for Mac and iOS

 

Every sound you don’t want is noise

 

HANCE provides machine learning algorithms that enhance audio in realtime. It removes sounds you don’t want and enhances the ones you do want. 

This is done by identifying the components in audio. We call this process Audio Source Separation. In 20 milliseconds it can learn which frequencies are voices, noises or reverb - and adjusts them according to what you want to hear. Sound familiar?

HANCE 2.0 now also identifies instruments in any audio-file. Meaning you can control the volume of the vocals, piano, bass and drums - listen to them exclusively, or remove them completely. Realtime stem separation.

With a library of 5MB and model sizes ranging from 3-4MB - HANCE is lightweight, low cost, and compute-efficient, which allows integration in both hardware and software.

How can this impact the music industry?

 

Karaoke, DJs and Musical Learning.

 

Realtime stem separation in hardware and software opens up for a plethora of opportunities.

  • Any song is now a karaoke song. Remove vocals with any device that can play music, and sing along to the original band in realtime. The process is so lightweight it can run on almost anything - even microphones!

  • DJs and producers thrive on stems, and while they excel at their manual digital dissection and mixing of music - Realtime Stem Separation makes their job a lot easier.

  • Musical learning. Remove instruments in realtime and play along.

 

These are just some use cases, and we are sure there are many others.

If you have an idea, we would love to hear from you. HANCE 2.0 is highly adaptable and teachable. We’re sure we can offer a solution.

Footnotes
Author
Tags
Share

Related posts

Phase aware source separation – overcoming the limitations of the ideal time-frequency magnitude masking

Phase aware source separation – overcoming the limitations of the ideal time-frequency magnitude masking

Spectrogram-based methods for source separation using neural networks typically estimate a separation mask that is multiplied pointwise with the...

Producing training sets for Extract: Dialogue by Acon Digital

Producing training sets for Extract: Dialogue by Acon Digital

This article summarises the extensive experimental work we have done to develop and build a data training set for Acon Digital’s Extract:Dialogue an...

Remix: The Next Step in Real-Time Audio Processing by Acon Digital and HANCE

Remix: The Next Step in Real-Time Audio Processing by Acon Digital and HANCE

Acon Digital and HANCE have partnered to launch Remix. This audio plugin operates on the HANCE Audio Engine, a cross-platform library with an easy...

MKBHD Showcases HANCE and Acon Digital’s Extract: Dialogue

MKBHD Showcases HANCE and Acon Digital’s Extract: Dialogue

We partnered with Acon Digital on Extract:Dialogue, which caught the attention of Ellis Rovin at the popular MKBHD YouTube channel, which, at the...

Why data safety is a competitive edge in AI

Why data safety is a competitive edge in AI

In recent years, with the growth of the artificial intelligence industry, people have shown concern for responsible use, privacy, and data safety. We...

Deep learning for audio applications

Deep learning for audio applications

Here at HANCE, we focus on the use of deep learning combined with digital signal processing. Our goal is to create solutions based on...