Just finished the whole series. I am a third year engineering student and this was really really helpful for my minor project. Thank you very very much Valerio, you're doing the lord's work
I've seen all the videos and wrote code with you. You're AMAZING! It was really interesting to learn all this stuff with you. I'm confident that it's not the last playlist I've seen on this channel)
Thanks to you, I have decided to direct my CS studies towards AI Audio Engineering. Thank you very much for this course and I hope you continue doing it :)
I have watched all the videos and would keep coming back to them. They have helped me a lot to build solid knowledge base for my AI features engineering for sound
Valerio, thank you very much for your effort, your wonderful explanations and the encouraging way you present really complex concepts. I finished the whole series and the videos are outstanding. Your work really makes a difference for me.
Thankyou so much for this very well explained series, loved following along to every bit of it! Hoping to use all the knowledge for my personal projects :))
I really enjoy the ride! One of the few educational playlist I can finish in less than a week, thank to how engaging your teaching style is. I learnt a lot and really appreciate your effort. :)
Thank You so much for this series Valerio .... Really loved it and now I am able to actually see the stuffs about audio waveforms. You are a great teacher :) !!
Thank you very much for all your efforts in making these videos and making such quality of content available for free. The videos were super easy to understand and clear. It was a great journey and I learned a lot of new things. Keep up the good work
Just binge-watched the entire series. I must say I am impressed by the way you teach. Thank you for making these videos, breaking down the complex topics and sharing your knowledge for free. I just have one question - Where should I go next? I mean what should be my next steps?
I have a question regarding feature extraction, in all of the examples you were extracting features for every frame, what resulted in the number of features dependent on the input size, for ML methods you need constant size input, how do you usually acheive that, do you calculate the mean, std, percentiles etc. or is there another way to use ML methods for the whole sound?
You have a good series here. You have primarily used functions as defined in librosa. One more value addition we can have in building a community can be through introduction to many more resources. I thought Queen Mary University of London had some interesting analytical tools for melody etc. May be they do not have to be taught at code level like this machine learning tools are. There can be some videos describing the range of capabilities of such audio and music analysis tools from good sources. This may help you build a community of practice that uses many tool sets. Music Technology Group of Universitat Pompeu Fabra, Barcelona also has some nice work going on.
Thank you for the feedback. I agree that some topics may be taught at a "higher" level. However, sometimes that is problematic. It's the typical divide between theory and application that university rarely overcome. With these videos, I aim to provide both sides of the coin.
Thanks a lot, I watched all the videos and learnt a lot's of things. I'm gonna try to add personal tweeks to the proposed features/try recoding them myself and compare results making sure I understood. I have a question though, is there any way you can create a sheet paper via python or anything free and generate the sound from it easily? Bonus points it it can automatized to create tons of samples. Anyway, I really enjoyed this serie and it taught me more than I expected, the explanations were crystal clear. Congrats man
Thank you for your series. I want to know if I have two clusters of audio data features, one is mel spectrograms, another is spectral centroid, how can you input them together to neural network to do an audio classification task about guitar pedals?
Hey Valerio! At 7:30, while using the frame to time function, you only passed the frames. Could you please explain how these conversions work for better clarity?
A have a question: Do you speak about the similarity about BW and Spectral spead, bur in this exmple the signals (or results) in BW and SC that's so closed (only final of the debussy it's so higher values to BW). In resume, whats the relationship or conceptual understanding that I have about each one and both? So ... Congratulations about your course in video series! I hope that you keep walking in our way to develop, sharing and creat a great link with people thar love audio, dsp, ai and all of them. haha Chers! :)
When I try to plot two audio files then a error occurs that is 'x and y must have same first dimension, but have shapes (2587,) and (2589,) error'. What should I do? and how?
FinallY !!!! Completed the whole playlist . Really got lots of knowledge from this. Now I ll jump to Deep learning for Audio Playlist and do some AI music Projs with help of ur channel github.com/Moonwalkerr/AudioSignalDSP-python , Here's my github repo link showcasing what i learnt till date form this series. THank You!
![🔴 ฟุตบอลแชมป์กีฬา 7HD แชมเปียน คัพ 2024 [รอบ 8 ทีมสุดท้าย] - ช่วงบ่าย](http://i.ytimg.com/vi/M0S_ReCIkxg/mqdefault.jpg)
Just finished the whole series. I am a third year engineering student and this was really really helpful for my minor project. Thank you very very much Valerio, you're doing the lord's work
Only cool peeps come this far. I hope everyone is doing good in their life. Cheers.
I've seen all the videos and wrote code with you. You're AMAZING! It was really interesting to learn all this stuff with you. I'm confident that it's not the last playlist I've seen on this channel)
Just finished the series. I really love the way that you broke down complex topics into very simple explanation.
Thanks!
Just went through all videos in this series. Very informative!
Thanks to you, I have decided to direct my CS studies towards AI Audio Engineering. Thank you very much for this course and I hope you continue doing it :)
I'm glad I could help :)
I just finished the series. WONDERFUL AND AMAZING
Thanks a lot for this series
Thank you Nitin! Be sure to subscribe to get more goods :)
I have watched all the videos and would keep coming back to them. They have helped me a lot to build solid knowledge base for my AI features engineering for sound
Your explanation througout this series was very clear and at the same time thorough. Thanks so much, I learned a lot!
Valerio, thank you very much for your effort, your wonderful explanations and the encouraging way you present really complex concepts. I finished the whole series and the videos are outstanding. Your work really makes a difference for me.
I'm really happy to hear this Oscar! This type of feedback is what pushes me to improve the content for this channel every day.
@@ValerioVelardoTheSoundofAI Hey Valerio.
Can one use mel filter banks to filter out the noise from an audio?
Thankyou so much for this very well explained series, loved following along to every bit of it! Hoping to use all the knowledge for my personal projects :))
I really enjoy the ride! One of the few educational playlist I can finish in less than a week, thank to how engaging your teaching style is. I learnt a lot and really appreciate your effort. :)
Thank you!
I learned a lot on audio processing in just two days, time to use this tools in my project. Thanks for your hard work. Cheers!!
Thank You so much for this series Valerio .... Really loved it and now I am able to actually see the stuffs about audio waveforms.
You are a great teacher :) !!
Thank you!
Thank you very much for all your efforts in making these videos and making such quality of content available for free. The videos were super easy to understand and clear. It was a great journey and I learned a lot of new things. Keep up the good work
Just binge-watched the entire series. I must say I am impressed by the way you teach. Thank you for making these videos, breaking down the complex topics and sharing your knowledge for free. I just have one question - Where should I go next? I mean what should be my next steps?
Also, I suggest you to join The Sound of AI Slack community (link in the description box)
@@ValerioVelardoTheSoundofAI I am already a member 😎
Thanks Valerio! Just finished the series this week, and I believe it’s gonna be a solid foundation for future studies!
Thank you! Stay tuned for more :)
You have been a great help in my research for a senior project, thank you.
Hi Valerio! Thank you very much for this series... It helped (and still helping) a lot on development of great intuition about audio processing.
I enjoyed watching this videos! Just finished it. thank you for amazing series!
Thanks!
Just finished the playlist! A journey indeed.
I have a question regarding feature extraction, in all of the examples you were extracting features for every frame, what resulted in the number of features dependent on the input size, for ML methods you need constant size input, how do you usually acheive that, do you calculate the mean, std, percentiles etc. or is there another way to use ML methods for the whole sound?
Thank you man! Your series hepled me to make my school project - voice control of Spotify.
This has helped my masters thesis in many ways. Thanks a lot.
Just completed this series, thank you so much. I learned a lot!
Hey Valerio, just finished the series! Great content, as usual :) Keep up the good work.
Finished the series in 2 days, thanks so much
Great series, thank you for providing this course absolutely free
Thank you very much for this series!! Helped me so much in my project
You have a good series here. You have primarily used functions as defined in librosa.
One more value addition we can have in building a community can be through introduction to many more resources. I thought Queen Mary University of London had some interesting analytical tools for melody etc. May be they do not have to be taught at code level like this machine learning tools are. There can be some videos describing the range of capabilities of such audio and music analysis tools from good sources. This may help you build a community of practice that uses many tool sets. Music Technology Group of Universitat Pompeu Fabra, Barcelona also has some nice work going on.
Thank you for the feedback. I agree that some topics may be taught at a "higher" level. However, sometimes that is problematic. It's the typical divide between theory and application that university rarely overcome. With these videos, I aim to provide both sides of the coin.
@Valerio Velardo You've done an excellent job! Thanks a lot for this great Series
You're welcome! Stay tuned for more ;)
@@ValerioVelardoTheSoundofAI I'm going to, you can count on it :)
Thanks a lot. It is very awesome series and help me a lot. And I think, I can go to my new job with more confidence
Thanks a lot, I watched all the videos and learnt a lot's of things. I'm gonna try to add personal tweeks to the proposed features/try recoding them myself and compare results making sure I understood. I have a question though, is there any way you can create a sheet paper via python or anything free and generate the sound from it easily? Bonus points it it can automatized to create tons of samples.
Anyway, I really enjoyed this serie and it taught me more than I expected, the explanations were crystal clear. Congrats man
Tnx for this series. that was so much helpful and easy to understand. thank u so much.
Thanks for such a great series. Much needed basics. Thanks again !!
👏👏 Thank you for this series!
Just finished up the whole series. Thanks a lot.
Thanks a lot Valerio sir, for such an informative and great series!
Thank you for your series. I want to know if I have two clusters of audio data features, one is mel spectrograms, another is spectral centroid, how can you input them together to neural network to do an audio classification task about guitar pedals?
I cant thank you enough for this series!
Fantastic series!
Thank you so much for the amazing series :)
Hey Valerio! At 7:30, while using the frame to time function, you only passed the frames. Could you please explain how these conversions work for better clarity?
Thanks a lot for this amazing series
A have a question: Do you speak about the similarity about BW and Spectral spead, bur in this exmple the signals (or results) in BW and SC that's so closed (only final of the debussy it's so higher values to BW). In resume, whats the relationship or conceptual understanding that I have about each one and both?
So ... Congratulations about your course in video series!
I hope that you keep walking in our way to develop, sharing and creat a great link with people thar love audio, dsp, ai and all of them. haha
Chers! :)
Thank you very much for this series. It help me a lot.
Fantastic content, thanks for sharing your knowledge!
When I try to plot two audio files then a error occurs that is 'x and y must have same first dimension, but have shapes (2587,) and (2589,) error'. What should I do? and how?
why do we need to extract and calculate centroid and spectral bandwidth?
You are fantastic
FinallY !!!! Completed the whole playlist . Really got lots of knowledge from this. Now I ll jump to Deep learning for Audio Playlist and do some AI music Projs with help of ur channel
github.com/Moonwalkerr/AudioSignalDSP-python , Here's my github repo link showcasing what i learnt till date form this series.
THank You!
That's awesome!
@@ValerioVelardoTheSoundofAI 😇😇
o7
Ssz
may i ask a question, what if i have a large number of audio files not just 2 ,3 how can i deal with them? thank you 🤍