Home > On-Demand Archives > Q&A Sessions >
Live Q&A with Alex Elium - Become A DSP Tuning Master and Build More Efficient Neural Networks
Alex Elium - Edge Impulse - Watch Now - DSP Online Conference 2021 - Duration: 29:58

That sounds very doable! I would recommend the MFE block over the MFCC one, as MFCC is more based on human vocal sounds and MFE is better for more generic sound.
Hello everyone, welcome! I'll be monitoring the questions now and will either answer with a comment for simple questions, or during the Q+A in about an hour for more lengthy responses. Enjoy!
15:18:19 From AllenK : Also "key" versus "monkey", where you see the correct sound, but it's not really what you want. 15:20:28 From Al Anway : It seems like early days for tuning, but as time goes on will there be published summaries of best settings that various people have found? Are there plans to establish a clearinghouse to collect and present them? 15:22:50 From Christophe Blouet : NN are used for years in sonar systems 15:23:19 From Christophe Blouet : same for vibrations 15:26:43 From Christophe Blouet : Very impressive demo, thanks a lot 15:28:54 From Radu Pralea : "Early days"... maybe, maybe not, we'll see (in restrospective), but we have to acknowledge CNNs for image and audio have also gone through some significant refinements during the last decade, with spectacular advances between iterations
Is it possible extract dogs noise and car noise in the open enviorments to counts dogs warning call