How to Extract Audio Features

แชร์
ฝัง
  • เผยแพร่เมื่อ 3 พ.ย. 2024

ความคิดเห็น • 112

  • @adi_1o1
    @adi_1o1 2 ปีที่แล้ว +13

    Some people are born to teach and your are one of them. It feels like finishing a semester course on signal processing in couple of mins.

  • @MathStatsMe
    @MathStatsMe 4 หลายเดือนก่อน +2

    I can't tell you how helpful this series has been in my current project applying CNN\LSTM to audio data. You've filled in all the gaps that are hard to find information about, as so many applications of CNN\LSTM are to image classification, not audio. Thank you!

  • @amruthgadag4813
    @amruthgadag4813 3 ปีที่แล้ว +11

    You made me clear the concept of frames, overlapping needs and multiple doubts.

  • @Hiyori___
    @Hiyori___ 3 ปีที่แล้ว +4

    I am so HAPPY I've found your video. No book could have explained this better, probably not even many professors or tutors. I'm gonna check your other videos!

  • @rajaniras1970
    @rajaniras1970 3 ปีที่แล้ว +3

    I am doing my research in Signal processing along with ML. Thank you for clearly explaining the concepts

  • @nokar999
    @nokar999 2 หลายเดือนก่อน

    Thank you so much for this series! I love how you hyperlinked the series by making references back to older videos to refresh material. Extremely useful.
    just a small note: I was reimplementing the Hann window in numpy for STFT and noticed that k should start at 0 and go to K-1

  • @sharonm1261
    @sharonm1261 3 ปีที่แล้ว +3

    thanks! great explanation of windowing and overlapping frames. I had to rewatch it a couple of times to understand how overlapping frames solved the windowing problem but so much easier and more fun than reading a book!

  • @priyanshipal9077
    @priyanshipal9077 3 ปีที่แล้ว +9

    Great series! You give a good overview of the process, the problems which we face and solutions while keeping the video duration short and optimum so one can keep watching the series. If one is curious enough, they can also read up more on the concepts as well. Great work, thank you! :)

  • @sathyanarayananvittal7832
    @sathyanarayananvittal7832 10 หลายเดือนก่อน +1

    Fantastic description. Loved the clarity in concept

  • @fujinafiul6044
    @fujinafiul6044 2 ปีที่แล้ว +1

    I just started yesterday and I am just loving it as it is helping me a great deal with understanding the audio concepts to do r&d on my ongoing work.

  • @ardavalilable
    @ardavalilable 2 ปีที่แล้ว +1

    I just love these videos, it clearly shows the theoritical part and simplifies it into a language that non specialist people (laymen) understands, I am by no means an audio engineer, though my field overlaps with the topics of sound/audio engineering, I work with machinery vibrations which uses basically every tool that you mentioned in this series, I am currently working on my thesis and have used some of these functions already along with wavelet packet transform (which makes my work so easy to do - and it took me quite time to get a hang of it). Great work, may your work help more people like myself for eternity (or till the climate change takes us all out)!
    Thank you again, and God bless!

  •  3 ปีที่แล้ว

    Perfect explanation which I could have not found for months on blogposts etc. Thanks!

  • @مهراسامدانلو
    @مهراسامدانلو 9 หลายเดือนก่อน

    Such a great series!
    You are an awesome teacher Velardo
    I appreciate you sooo much :)

  • @namanagrawal9765
    @namanagrawal9765 ปีที่แล้ว +1

    You're an amazing teacher, thanks for the videos! They are really helpful to me!

  • @kobyfr
    @kobyfr ปีที่แล้ว

    Thank you very much for these videos.
    It is very generous of you to make them.
    I think there is another aspect of spectral leakage and that is if the signal harmonics do not fall exactly " on top of" the sampling frequencies, then the energy of the harmonics gets spread out to the ALL sampling frequencies, with the most of the energy leaking to frequencies around the closest sampling frequency.

  • @jaypople8885
    @jaypople8885 5 หลายเดือนก่อน

    That's exactly what I was looking for, you made my day thanks☺

  • @MrOpossumx3
    @MrOpossumx3 3 ปีที่แล้ว

    Amazing intuition over why using windowing mitigate spectral leakage, great series of videos!

  • @唐中倫
    @唐中倫 3 ปีที่แล้ว +1

    Excellent Explanation Solved all my problems Thank You Sir!

  • @4abdoulaye
    @4abdoulaye 4 ปีที่แล้ว +1

    Well explained for overlapping and signal loosing done by Hann windows. Thanks

  • @yuvaramsingh3773
    @yuvaramsingh3773 4 ปีที่แล้ว +1

    i like your work . i have worked with DL and image for quite some time. your series showed me all i need to know abt sound . thanks and keep doing this

  • @hlamzar
    @hlamzar ปีที่แล้ว

    This is awesome explanation. now i understand why you can't use a digital filter thats just rectangular

  • @rekreator9481
    @rekreator9481 3 ปีที่แล้ว +2

    I can feel this is highly inspired by Mullers book about Digital Signal Processing :DD I used it for my thesis and I recgonized a lot of stuff like... Ive heard (read) this somewhere before :DD But its described very well there and you explained/summarized it perfectly ;)

  • @yashdeepshetty3401
    @yashdeepshetty3401 3 ปีที่แล้ว

    Best teacher ever 🙏🙏

  • @tiagoramos121
    @tiagoramos121 3 ปีที่แล้ว +2

    Very nice!! Thanks a lot!! Just an observation: in the middle of the video, i got surprised by a slack ring hahaha ... i couldnt find any slack notification in my phone and take a while to discover that the sound comes from de video. That's all . Minute 12:42

  • @TheRainshine79
    @TheRainshine79 4 ปีที่แล้ว +3

    Thank you for the awesome explanation. Very clear and understandable! :)

  • @markusbuchholz3518
    @markusbuchholz3518 4 ปีที่แล้ว +2

    OMG. You and your channel are unique. Amazing. Thanks

  • @juniorsilva5713
    @juniorsilva5713 7 หลายเดือนก่อน

    Thank you very much, Valerio!

  • @TheMagicmagic290
    @TheMagicmagic290 3 ปีที่แล้ว +3

    if you have overlapping frames, given that you apply the hann window function, wouldn't you create some form of amplitude modulation that is not present in the original signal?

  • @venkatesanr9455
    @venkatesanr9455 4 ปีที่แล้ว +1

    Enjoyed as usual.... and waiting for the next

  • @مهراسامدانلو
    @مهراسامدانلو 9 หลายเดือนก่อน

    I really enjoyed your explanations

  • @tanyajain3068
    @tanyajain3068 2 ปีที่แล้ว

    Incredibly helpful! It would be immensely helpful if you could post a video of the code for framing and windowing for an audio with the explanation.

  • @rakshithv5073
    @rakshithv5073 3 ปีที่แล้ว +1

    In Frequency domain,If overlapping frames are introduced to compensate the loss of signal during windowing why do we have overlapping of frames in time domain ?
    Whether discontinuity(Spectral leak) happens only at the end or start of the frame ? Is it only relevant for frequency domain ?

  • @hamidmojarrad
    @hamidmojarrad 4 หลายเดือนก่อน

    You teach so well.
    I have a question. I’m going to detect phonological feathers of African American English from some interviews, and I want to make the detection process automated. What do you recommend?

  • @vaibhavdixit4377
    @vaibhavdixit4377 ปีที่แล้ว

    Big thumbs up, solid video brother!

  • @nerd3788
    @nerd3788 3 ปีที่แล้ว +1

    how to choose overlap length? if it was more than required then wouldn't a part of signal repeat?
    if i understood correctly, then it doesn't matter as we are extracting features from stft of each frame. is it this way?
    and also ur videos r really good

  • @esthermdzitiro31
    @esthermdzitiro31 4 ปีที่แล้ว +1

    Super helpful, thank you for the great work.

  • @diamondcutterandf598
    @diamondcutterandf598 ปีที่แล้ว

    11:56 i'm kinda lost. what do u mean by "not an integer number of periods"?

  • @haitranminh6307
    @haitranminh6307 3 ปีที่แล้ว +2

    Hi sir, we apply the overlapping because of the spectral leakage when we apply the FFT for the frequency domain. But in time domain, this is not the case.
    Then why do we still apply the overlapping in the time domain? Thank you, sir

  • @ridamsrivastava9502
    @ridamsrivastava9502 4 ปีที่แล้ว +1

    Highly comprehensive and informative series!
    I had a question : How can we directly input Low Level Descriptors to Keras models?

    • @ValerioVelardoTheSoundofAI
      @ValerioVelardoTheSoundofAI  4 ปีที่แล้ว

      You can check out my "DL for Audio with Python" series for that. In this series, I don't use Keras, and focus only on audio features.

  • @tetlleyplus
    @tetlleyplus 10 หลายเดือนก่อน

    According to the sampling theorem, a signal must be sampled at least twice as fast as the highest frequency component in the signal, but in practice what are the recommended sampling frequencies?

  • @SAWLENE44
    @SAWLENE44 3 ปีที่แล้ว

    Wow! This is so good. Wish I had seen this before. Merci! :)

  • @maipyaar
    @maipyaar 3 ปีที่แล้ว

    Thank you for this awesome series. Please, what is the difference between frame and window size? These two terms confuses me alot

  • @dhruvbishnoi8840
    @dhruvbishnoi8840 4 ปีที่แล้ว

    Thank you! I hope I will get a better rank with this information :)

  • @kewtomrao
    @kewtomrao 3 ปีที่แล้ว

    This is hands down the best tut series!
    Where did you learn so much?
    Could you recommend]nd some books or websites?
    Thank you!

  • @凌璃-b8z
    @凌璃-b8z 3 ปีที่แล้ว

    Thank you through I don't understand. I read other artical extraly to learn it. However, you help me much. I never reliaze leakega in FFT before. LOL

  • @Bigman74066
    @Bigman74066 4 ปีที่แล้ว

    Very good, thanks for this video!

  • @rightcurve
    @rightcurve 2 ปีที่แล้ว

    Great content! After Windowing(overlapping) you can minimize the "lost period", but it does not seem to solve losing signal problem. To me, by applying Haan function, edges in original signal are lost anyway.
    So I am not fully sure what we have truly achieved after overlapping, except minimizing useless/lost signals? Frequency Domain will still be missing bars for those overlapped portions of frequencies, isn't it?

  • @heddshot87
    @heddshot87 ปีที่แล้ว

    I assume spectral leakage simply means a "click/pop" from clipping when abrupting the sample?

  • @YarkoFFXI
    @YarkoFFXI ปีที่แล้ว

    I'm a bit confused about the denominator in the Hann windowing function. Shouldn't it just be K, i.e. the frame size, or number of samples in a frame, instead of K-1?

  • @dionisiuspratama7152
    @dionisiuspratama7152 3 ปีที่แล้ว

    Thank you for your explanation! Sorry, but may I have the book you are referencing to for this video?

  • @notallama1868
    @notallama1868 ปีที่แล้ว +1

    So if I'm understanding correctly, the main purpose of windowing is to deal with spectral leakage. But it sounds like spectral leakage only occurs at the beginning and end of the entire signal. So why bother windowing every frame? It seems like we could save a lot of time and effort by just clipping the erroneous bits off the ends of the signal. I'm guessing there's a reason, but what is it?

    • @saurabhdeshmukh2182
      @saurabhdeshmukh2182 11 หลายเดือนก่อน +1

      As per my understanding, your suggestion will work only for static waveform. But in order to calculate Spectrogram (STFT) we need to calculate FFT at every frame and collectively we will get a nice spectrogram to work with.

  • @daviddemmers130
    @daviddemmers130 ปีที่แล้ว

    Around 19:39 you explain what hop-length and the frame size is.
    But very confusing the librosa package has different feature names and also another new feature n_fft
    Could you clear up what the n_fft means and how they are different.

  • @beto5720
    @beto5720 4 ปีที่แล้ว +1

    Great video mate, I've seen Librosa use 2048 for frame size and 512 for hop size as default for many of their functions (ej. melspectrogram). Any recommendation on what to use as a general reference? I'm not sure how Librosa does their windowing though so idk.

    • @ValerioVelardoTheSoundofAI
      @ValerioVelardoTheSoundofAI  4 ปีที่แล้ว +1

      A usual ratio between frame size and hop length is 2:1. Beyond this it's difficult to provide a general rule. For some problems you want higher temporal resolution, hence you should use a hope size of 512. For others, 768 or 1024 is totally fine. You'll have to treat the hop length as a hyper parameter that needs to be optimised empirically during training.

    • @beto5720
      @beto5720 4 ปีที่แล้ว +1

      Valerio Velardo - The Sound of AI
      thanks! I’ve noticed that it varies indeed so I’ll keep playing around with it.

  • @tyhuffman5447
    @tyhuffman5447 4 ปีที่แล้ว

    Very good stuff. Thank you.

  • @ceyhunyldrm7392
    @ceyhunyldrm7392 2 ปีที่แล้ว

    Hello, my friend, I didn't get the point and I wanna ask you.
    Let's say I have extracted 30 windows overlapping from the audio signal. while I am extracting features should I act these 30 as a different 30 windows but the same target or 30 windows = 1 feature x 30 times = 30 features => my audio.
    which one do you think is true?

  • @blaze-pn6fk
    @blaze-pn6fk 3 ปีที่แล้ว

    as usual, amazing stuff.

  • @CULTURE_dz
    @CULTURE_dz 4 ปีที่แล้ว +1

    hello sir, can you help me with some links to do windowing to pick speech or audio from microphone
    for preprocessing , and can you make a tutorial for this soon please
    thanks

    • @ValerioVelardoTheSoundofAI
      @ValerioVelardoTheSoundofAI  4 ปีที่แล้ว +1

      That's something I'd like to cover in the future. Stay tuned :)

    • @CULTURE_dz
      @CULTURE_dz 4 ปีที่แล้ว

      @@ValerioVelardoTheSoundofAI.. Ok , i am your student thanks

  • @mishachandar3965
    @mishachandar3965 4 ปีที่แล้ว

    Great content delivered! Keep going !!!!!

  • @myloveallmine_
    @myloveallmine_ 6 หลายเดือนก่อน

    thx for your help i can better understand audio analysis

  • @Waffano
    @Waffano 2 ปีที่แล้ว +1

    @12:00: What exactly does it mean that "Processed signal isn't a integer number of periods"? I get that if you loop the sound frame that is showed on the slide, it does not result in a continous wave but it goes from around -3 amplitude directly to around +4 which results in a high frequency, but i cant really get what is meant by "Processed signal isn't a integer number of periods". Can someone help please? :)

    • @Waffano
      @Waffano 2 ปีที่แล้ว

      @Andrei Thank Andrei. I realised what confused me is that I didn't know that a period was an actual feature of the sound wave. Thought it was more abstract than that.

  • @Drew_7
    @Drew_7 ปีที่แล้ว

    At 3:51, could you explain how you go this number again? I tried to do the calculation, but I'm not getting the same thing. Is this because of A/D conversion? Is that single sample number based off of a sample/hold technique or is it just a normal length for one sample in a "one second" length?

  • @6tyelement979
    @6tyelement979 4 ปีที่แล้ว

    Hi please what is the difference between short term and mid term feature extraction. Is mid feature extraction like averaging the short term frames ?

  • @rustombhesania7265
    @rustombhesania7265 3 ปีที่แล้ว

    17:56 was the ahHaa moment for me , loved it thnx for making the video

  • @josecosta3878
    @josecosta3878 2 ปีที่แล้ว

    Is there any videos where you show how to extract and measure silent pauses with Librosa or another Python library? I would appreciate your help. Thanks.

  • @elyorjonmannonov6114
    @elyorjonmannonov6114 4 ปีที่แล้ว

    Hello Valerio. Thank you for another great video. I would like to ask for your advice for my project and already emailed you about it. Could you take some time and give your thoughts on it please? Would really appreciate it. Thank you

  • @missestherm9454
    @missestherm9454 4 ปีที่แล้ว

    Hie. great video. are time-frequency domain audio features extracted at the same time or one then the other ?

    • @ValerioVelardoTheSoundofAI
      @ValerioVelardoTheSoundofAI  4 ปีที่แล้ว +1

      Usually, you'll extract them at different times. In audio processing libraries like Librosa, there are different functions for different audio features, that you can apply sequentially. Or, perhaps, you may just want to extract one!

    • @missestherm9454
      @missestherm9454 4 ปีที่แล้ว

      Valerio Velardo - The Sound of AI Thank you.

  • @tyhuffman5447
    @tyhuffman5447 4 ปีที่แล้ว

    Valerio, I'm using your code on my github python notebook to process some machine sounds and I want to give credit where credit is due so I'm going to mention you, the book you're working on, and the YT series and a link to the YT series. Is that good enough for you? Would you like me to add anything else? I'll make a boilerplate that I will put at the top of the code.

  • @DANstudiosable
    @DANstudiosable 3 ปีที่แล้ว

    Can u please explain spectral leakge in layman terms here?

  • @DEEPAKYADAV-vb2ee
    @DEEPAKYADAV-vb2ee 3 ปีที่แล้ว

    Can you tell me the whole feature extraction pipeline for audio data. Like I wank make a class of feature extraction. Which take audio signa. Then what I have to do?

    • @ValerioVelardoTheSoundofAI
      @ValerioVelardoTheSoundofAI  3 ปีที่แล้ว

      I covered audio preprocessing pipelines in this video: th-cam.com/video/O04v3cgHNeM/w-d-xo.html

  • @missmudassarnizam5158
    @missmudassarnizam5158 4 ปีที่แล้ว +1

    thankyou make this video basic information...

  • @lucasa.w.romeiro2136
    @lucasa.w.romeiro2136 2 ปีที่แล้ว

    Hello my Name Is Lucas. I'm Brazilian and I'm trying to make an algorithm that differentiates one noise from another.
    For example: Depending on the sound the rain makes as it hits the ground if I can determine how much water is falling. Things like that, always involving noise.
    Anyone familiar with this to help me with some directions?
    Thanks

  • @4abdoulaye
    @4abdoulaye 4 ปีที่แล้ว

    But I noticed an error in slide title, First you titled them as Time domaine 2:49 example then at the end you titled them Frequency domain 20:41.

    • @ValerioVelardoTheSoundofAI
      @ValerioVelardoTheSoundofAI  4 ปีที่แล้ว +1

      Thank you for pointing that out!

    • @4abdoulaye
      @4abdoulaye 3 ปีที่แล้ว +1

      @@ValerioVelardoTheSoundofAI I re-watched the video this is nit a mistake.

  • @thechuong1448
    @thechuong1448 3 ปีที่แล้ว

    Super!

  • @matveysafronov2813
    @matveysafronov2813 2 ปีที่แล้ว

    thaks!
    ps: i think you need nerdy music in the intro. mozart i think )

  • @aashansamuel1173
    @aashansamuel1173 4 ปีที่แล้ว

    Can you please tell how to extract features from an audio signal by using MATLAB?

  • @svalente2524
    @svalente2524 3 ปีที่แล้ว

    this is all very cute but how to we actually implement these things? seems like everybody talks about them, but nobody shows it

  • @shafagh_projects
    @shafagh_projects 3 ปีที่แล้ว

    perfect!

  • @이종법-o2m
    @이종법-o2m 2 ปีที่แล้ว

    please make a video list

  • @chacmool2581
    @chacmool2581 2 ปีที่แล้ว

    Spectral leakage. Spectral contamination is more like it.

  • @saigeeta1993
    @saigeeta1993 4 ปีที่แล้ว

    Hello, Sir SaiGeeta here from India. Sir, please suggest me good laptop specification for text to speech synthesis using Deep learning algorithm. please please

  • @leophysics
    @leophysics 4 ปีที่แล้ว

    Most of us are indian and I am too ..