How can we understand what are the available Hexagon SDK libraries for audio processing
We are interested in echo cancelation, beamforming and wakeword identification.
Apprecaite if you can point us to the right place
I
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Hi,
Can you please elaborate your query. What kind of libraries are you looking for? Do you want to integrate the above mentioned custom modules in audio path?
Thanks,
Thanks for the prompt reply.
Yes we want to intergrate those into the audio path.
We are looking to accomplish echo cancelation, beam forming and wakeup word detection.
At the building blocks level for the beamforming (MVDR) we assume the need for the follwoing: FFT, matrix multiplication, matrix inversion (hopefully not, but if so than small matrices) , spectrum estimation, eigen value decomposition (small matrices ~8X8), dot products.
Not sure if you need this level of description or something else. Please let me know.
Thanks,
Itai
Hi there
It has been long since you have posted this question, but did you already find a way around it? It would be super helpful as I am trying to also carry out something similar and with the lack of support in this forum, the task seems more and more daunting. Any help would be beneficial.
Best
Somu