L-Acoustics has announced Source Intelligence, a real‑time vocal enhancement technology that isolates the human voice from background noise, using a unique source separation algorithm. Running on the trusted L‑ISA Processor II Core, Source Intelligence removes crowd noise, instrument bleed, PA spill, and room reflections. The function removes up to 40 dB of extraneous signal, which in turn reduces the risk of feedback.
The machine learning algorithm accomplishes this by continuously identifying the voice as different sources of audio enter the vocal microphone, removing what is not consistent with the constant tone and range of the singer. With greater vocal isolation and unrivalled audio quality, engineers gain the freedom to mix more creatively, while performers and presenters have the freedom to move anywhere on stage- even in front of the PA- without sacrificing clarity, presence, or risk of feedback.
“For decades, engineers have been solving the PA bleed and feedback problem with compromises like notch filters that color the sound, expanders that can be unpredictable, or staging layouts that pull performers away from the audience,” explains Ryan John, Director of Product Management, Software at L-Acoustics. “Source Intelligence removes that trade-off entirely. The machine is continuously listening and continuously working, so the engineer can focus on the mix instead of fighting feedback, and the performer can own the whole stage.”
This isolation essentially allows for studio-level intricacy during performances. Functions such as EQ and reverb will not be interrupted by other instruments or noise sources, allowing the live engineer to dial in the vocal based on their unique delivery and the current environment.
Intuitive Controls
- Four instances
- Independent controls for refinement of high and low frequency content
- Input/output via MADI, AVB or AES
Unrivaled Performance
- Up to 40 dB of non-voice signal reduction
- Consistently rated the highest quality output in blind tests
- Hundreds of hours of continuous testing with no reduction in audio quality
Optimized for Live Sound
- Latency of under 8.5ms
- Designed for seamless integration in L-Acoustics systems only
- Extensively validated on major tours and productions, with no perceived impact on performance
With vocals central to the majority of live performances, Source Intelligence has already drawn acclaim from engineers industry-wide:
“Source Intelligence gives me a vocal sound like no other. It’s basically studio-quality vocals now, which changes the game completely,” says Joey Diehl, FOH engineer for Benson Boone.
“I’m very impressed with how much headroom it gives me. I was able to get crisp, clean vocals in any scenario- including very loud stage environments and actors in front of the PA,” says Cody Spencer, Tony Award-winning sound designer.
