Yes, the center position in the Instamic also uses multiple MEMS. I think that's done to improve noise performance over what would be available from a single sensor that is physically small and thus inherently noisy. Also means improved noise performance from sensors run in parallel applies only to mono mode, not stereo mode. Since the unit does allow for 32bit float recording in stereo mode, post analysis should be able to show the actual dynamic range of the mono modes verses the stereo mode.
Do you know if it uses dual channel switching ADCs? If it is, it might be operating like the Deity PR2 does, using the two ADCs in dual switching mode when recording in mono, while reverting to using them in single non-switching mode for stereo. Can store output as 32bit float either way of course.
I hope that simply quoting what AI told me about multiple MEMS mics the other day won't get me expelled from the forum, but I asked it "How do they get stereo audio from closely spaced MEMS mics? Aren't they omnidirectional?" The answer was as follows -
"You’ve hit on exactly why MEMS (Micro-Electro-Mechanical Systems) microphones seem like they shouldn't be able to do stereo or directional audio well.
You are entirely right: the individual MEMS capsules themselves are almost always omnidirectional. Because they are incredibly tiny and sealed into surface-mount chips on a circuit board, they naturally pick up sound equally from all directions.
To get stereo or directional audio out of them—like the distinct left/right separation or beamforming you get in modern smartphones, laptops, and smart speakers—engineers don't rely on the physical shape of the microphone capsule. Instead, they use a combination of acoustic porting and digital signal processing (DSP) algorithms.
Here is how they turn closely spaced omni mics into a high-functioning stereo or directional array:
1. The Math of Micro-Delays (Phase Differential)
Sound travels at roughly 343 meters per second. When a sound wave approaches two MEMS microphones spaced even just a few centimeters (or millimeters) apart, it will arrive at one mic fractionally sooner than the other.
This creates a tiny Time of Arrival (ToA) difference and a corresponding phase shift between the two audio signals.
For Spatial Stereo: The DSP calculates these minute phase and volume differences to recreate a stereo image for your headphones or speakers, mimicking how our two ears perceive spatial direction.
For Beamforming (Directionality): If the system wants to focus on your voice and block out background noise, it can intentionally delay the signal of one mic so it perfectly aligns with the other. When added together, your voice gets louder (constructive interference), while sounds coming from the sides end up out of phase and cancel each other out (destructive interference).
2. Dual-Port Acoustic Design
Sometimes, directionality is built right into the physical design of the device before the software even touches it. This mimics how classic studio directional microphones work.
A phone or smart device might use a MEMS mic with two acoustic ports (holes)—one on the front of the device and one on the back. Sound from the rear has to travel slightly farther to enter the internal cavity of the mic. By the time it hits the tiny silicon diaphragm inside, the sound waves from the front and back meet and partially cancel each other out, physically creating a cardioid (directional) pickup pattern out of an omni sensor.
3. Smart Software Overcoming Physical Limitations
Because MEMS mics are so close together in modern gadgets, the natural acoustic separation (the "stereo width") is technically very narrow. If you just routed Mic A to the left channel and Mic B to the right, it would sound almost like mono.
To fix this, the DSP applies spatial extraction algorithms:
Frequency-Domain Processing: The software splits the audio into numerous frequency bands. It analyzes which frequencies are dominant in the phase-lead of Mic A versus Mic B.
Stereo Expansion: The algorithm artificially exaggerates these differences, digitally widening the stereo field so that a sound originating from the far left actually sounds like it's coming from the far left when played back.
The Big Advantage
While this sounds like a lot of digital trickery, MEMS microphones have one massive advantage over traditional electret studio mics that makes this possible: consistency.
Because they are etched out of silicon wafers in semiconductor factories, millions of MEMS mics can be produced with nearly identical frequency and phase responses. This extreme uniformity allows DSP chipsets to perform precise mathematical calculations on the signals without having to worry about one microphone capsule sounding naturally brighter or darker than its neighbor."
You may respond by telling me that you were completely aware of all that...
As for whether it used dual ADCs - well, I tend to think that Zoom's policy on that may extend to other companies, namely that if they don't claim it, it's just a single ADC. I occasionally have email interchanges with Insta360 about technical matters - eg when they claimed a new camera had stereo audio when it obviously didn't, and they had to change their advertising, and a fake option in firmware! - and I might see if they cared to divulge anything about the exact implementation of MEMS and the whether it has a dual ADCs.
Topic: Insta360 Mic Pro - New wireless mic with 32-bit stereo internal recording (Read 2021 times)