Mic array performance compared to ReSpeaker

Looking for primarily a mic array platform to embed Amazon’s Alexa Voice Service into for a sleep tracker… How does the 8 mic array in the Matrix Creator compare to the ReSpeaker Mic array?

Does it feature on chip Beamforming, Noise Suppression, De-reverberation & Acoustic Echo Cancellation like the ReSpeaker…

Can’t find performance characteristics in the documentation: https://matrix-io.github.io/matrix-documentation/Hardware/API/microphone/ just get a 404…

Any response on this? I am looking to buy this primarily for the microphone array, and re-speaker seems to be more focussed on this. Anyone from Matrix can reply here? This is such a great platform. I wouldn’t want to buy something else just because of better advertising. Thanks!

I’m also interested in a comparison between the two, although having (potential) Z-Wave support in the matrix creator is a definite plus for me.

It would really be great if anyone could share some insight between these two.

1 Like

+1 … this would be very useful information

+1 for those who are undecided

I have heard from a contact @ Matrix.One … that Matrix has the above capabilities mostly working for their proprietary consumer device. Will matrix.one please share the source code or libraries (to achieve above) with the developers? Especially far-field improvements. TIA for reading guys!

Yes to your question. According to Matrix the following is supported

Beamforming, Noise Suppression, De-reverberation & Acoustic Echo Cancellation

Additionally, acoustic source localisation, far field vouce capture and more…

Info here: https://www.indiegogo.com/projects/matrix-voice-open-source-voice-platform-for-all#/

Edit: This is for the new voice product, not sure about creator

Thanks, but can anyone from the company answer the initial question if the Matrix Creator has all those features.

According to https://github.com/matrix-io/matrix-creator-malos/issues/87 we don’t have for instance echo cancellation on Matrix Creator.

Can we please get an overview what is implemented and what not? Otherwise one can use my 10$ microphone for the same purpose.

Did anyone ever get feedback from MATRIX on this? I’m looking into the same thing and I don’t see much data on the difference between these two platforms or the more general discussion of an FPGA based system (VOICE) and an ASIC based system (ReSpeaker.)

im here to bump this question again!

As far as I can see from the code commits and several toxic threads on this forum, Matrix products have only a simple beamformer implementation so far, despite the unsubstantiated description on the official site that they support all DSPs. I personally have a Matrix Voice (esp32) board and a couple of ReSpeaker Core v2 boards.

None of these 2 provides all the DSPs out of the box. But SeeedStudio has a partnership with Alango company which ships their VEP package (wrapped into librespeaker library) with ReSpeaker Core v2 (as a separate deb package though).

I have tested mostly all the DSP algorithms on ReSpeaker Core v2, and can conclude the following:

  • NS and AGC work well;
  • AEC works imperfectly (they actually suppress the output: ~20dB), so you can still hear the background music; it works well if your speaker is configured to ~70% volume level and there are no bass’ peaks that affect the preprocessed audio quality; however, the peaks’ issue can be workarounded via decreasing the volume programmatically while KWS triggering;
  • KWS is good (with default keywords though);
  • Beamformer with DOA works well for a single audio input; but if you have several distractors (like TV), it doesn’t work as expected (focusing the beam which triggered the wake word);
  • VAD doesn’t work as expected, as any noise is treated as a voice activity.

On the Matrix side, we have only a primitive beamformer that can’t handle multiple input sources as well. But you can also add KWS from wakenet. Of course, if you plan to use Matrix Voice as a Pi Hat, you can add more algorithms on your own, but it doesn’t seem like a reasonable investment.

You can find a WS streaming service that reveals mostly all the DSPs for the ReSpeaker board on my GitHub.

And the same thing, but for Matrix Voice.