3 - Audio Feature Extraction using Python

Рет қаралды 40,803

2 жыл бұрын

In this video, we focus on audio feature extraction in the frequency domain.
The code shown in the video can be found at my Github page:
github.com/PrabhjotKaurGosal/Helpful-scripts-for-MachineLearning/blob/main/AudioFeatureExtraction_vX.ipynb
Helpful Resources to get more technical depth for some of the terms mentioned in the video/code are referenced throughout the jupyter notebook at the link above. Some of those are also mentioned below:
What is a Spectrogram?
kzfaq.info/get/bejne/layRp9t4s5nacYE.html
www.phon.ucl.ac.uk/courses/spsci/acoustics/week1-10.pdf
What is windowing?
download.ni.com/evaluation/pxi/Understanding%20FFTs%20and%20Windowing.pdf
What is Short Time Fourier Transform (STFT)?
kzfaq.info/get/bejne/nqxnZdaKnJbDeYU.html
What are MelSpectrograms?
kzfaq.info/get/bejne/b614dsyaqbKsgWg.html
kzfaq.info/get/bejne/nqxnZdaKnJbDeYU.html
medium.com/analytics-vidhya/understanding-the-mel-spectrogram-fca2afa2ce53

Пікірлер: 37

@fuchunhsieh7396 8 ай бұрын

this is a really helpful video for someone who just starts trying to do signal processing and classifying, thank you for your effort and it really helps me understand better on spectrogram and signal processing!

@soumyadrip 2 жыл бұрын

Thank you for the video. Very excited for these video series. One of your videos, yolo to coco conversation was very helpful.

@prabhjotgosal2489 2 жыл бұрын

I am glad you find the content helpful. Thanks for the feedback!

@kashan-hussain3948 Жыл бұрын

Thank you for sharing your effort.

@lindaflow5434 3 ай бұрын

this was really helpful! thank you very very much!!

@PlabonTalukder 11 ай бұрын

Thanks for the video!

@vialomur__vialomur5682 10 ай бұрын

Thanks a lot for this!

@jamilamuhammad5717 Жыл бұрын

Hello Prabhjot, this is indeed an amazing work. Thank you for taking your time to share knowledge to the world. Could you please guide me on how to save batches of spectrograms? I have created TensorFlow dataset of audio files and pass them through a data pipeline inline with the kind of decoding in accordance to my work. I want to plot and save each spectrogram from the dataset generated. Thank you in anticipation of your kind response. Cheers!

@sawinderkaur5057 2 жыл бұрын

Excellent Keep it up beta

@drjfilix3192 Жыл бұрын

Hi Prabhjot Gosal, thank you for your hot video which turned out to be very interesting! a practical case: if I have to change the bpm of a song to make them constant for its entire duration (avoid drifting tempo) How tight is my library?

@prabhjotgosal2489 Жыл бұрын

Hi, Thanks for the comment! I am not well versed with processing music audios and cannot help at this time unfortunately.

@Techieadi Жыл бұрын

Just shrink the song. A 100 bpm shrink by 25% will result in 75 bpm

@Dr.AhmedQusaySabri 11 ай бұрын

Thanks a lot

@devisthesis343 2 жыл бұрын

hi. can I have the slide presentation?really nice presentation in 5:47 you mention spectral leakage, what is exactly?

@hydraulicgames2493 Жыл бұрын

I think that's the signal that is 'lost' when converting from analog to digital.

@SvSzYT 5 ай бұрын

if you want to increase the resolution on the x axis you can increase the sr. But how do you increase the resolution of the frequency on the y axis?

@KhanhNguyen-dn8bm Жыл бұрын

Hi Prabhjot , can you make a video about LPC algorithm in Feature Extraction please?

@prabhjotgosal2489 Жыл бұрын

Hello, I sure will. It might take some time though as I wrap up the direct speech to speech translation project.

@demkut 7 ай бұрын

I want to analyze a frequency signal with a fairly large bandwidth. Will this method suit my task?

@simhan2895 Жыл бұрын

Hi, Good Day. Can we use this audio feature extraction to compare two voice of a same speaker in terms of authentication? Will saving the log mel output as logMel.out and compare the same speaker voice in different time as logMel2.out and compare both these output to authenticate ? Is that possible and result in a good way for this use case? Regards, Simhan

@prabhjotgosal2489 Жыл бұрын

Hi, It is certainly possible to compare the two log mels and they may yield what you are looking for. However, MFCC features are better features for speech in general, compared to the log mel spectrograms. Thankks!

@simhan2895 Жыл бұрын

@@prabhjotgosal2489 Thanks for your response. Do you have any references for MFCC feature extraction ? It would be of great help for my research.

@prabhjotgosal2489 Жыл бұрын

@@simhan2895 , this video maybe helpful: kzfaq.info/get/bejne/jbB5YJRosrTUlHk.html

@juicetin942 Жыл бұрын

Hi Prabhjot, I want to compare audio of person A with audio of person B and get a match percentage. Can you guide how to achieve this? Just pointing me in the right direction will be great help.

@prabhjotgosal2489 Жыл бұрын

Hi, you may want to check out pypi.org/project/speaker-verification/ I have not tested it myself but this could be a good start.

@juicetin942 Жыл бұрын

@@prabhjotgosal2489 I went through this, sorry my question was wrong. I don't want to verify the speaker, I want keep person A as reference and then match pronounciation of Person B with A. Then get a percentage match score.

@prabhjotgosal2489 Жыл бұрын

@@juicetin942 Very interesting problem! I can think of few things which may or may not work depending on the dataset. I would start with the basics: 1. Use cross correlation to compare two audios (en.wikipedia.org/wiki/Cross-correlation). 2. Compare the spectrograms of the two audios (first convert each of the audio waveform to their respective spectrogram and then find the difference between two spectrograms). The difference spectrogram will indicate how different the two audios are. 3. Formulate this as a template matching problem. The audio (waveform or its spectrogram) of person A can be considered as a template. Then, the goal is to find how much the audio of person B matches with this template. Look for research papers in CV space for template matching. Please note this problem becomes harder if the two audios are drastically different because then we need to deal with many more variables besides the pronunciation differences. Such as different recording environments (which means we have to deal with the different background noise), different audio lengths (if the content in the audios is the same but it is said at different timestamps in the audios), different speaker voices, etc.

@juicetin942 Жыл бұрын

@@prabhjotgosal2489 Thank you

@user-jq3ig9hu1m Жыл бұрын

is it possible to share a link to the 'h_1.wav' file used in your youtube demo please 🙂

@prabhjotgosal2489 Жыл бұрын

I have uploaded the sample file on my github page: github.com/PrabhjotKaurGosal/Helpful-scripts-for-MachineLearning

@Bekeyurious 8 ай бұрын

hello, its really helpful but can you please tell me how should i run the code and where? (ik silly question but im new to it)

@prabhjotgosal2489 8 ай бұрын

Hi - The code can be run either in a jupyter notebook or Google Colab. Colab might be easier if you don't already have python/jupyter notebook installed. To run the code in the Colab, just download the code file from my github and drop it in your google drive. Then adjust the file paths, etc. I hope this helps!

@durgaganesh423 Жыл бұрын

Hi Very interesting I have a query How can we find audio abnormalities like Missing samples specific duration And glitches in between audio file Could help me Thank you adavance

@prabhjotgosal2489 Жыл бұрын

Hi, that is an interesting question... If by missing samples, if you mean the audio is silent for a specific duration, then that is easy to detect. We can simply check for where the amplitude is 0. For the glitches, it will be a little trickier in my opinion as we would need some way of telling whether a spike/abnormality in the audio is part of the audio or is it truly a glitch. If you have a footprint of what a glitch looks like, then you could check if your audio has a similar footprint.

@durgaganesh423 Жыл бұрын

@@prabhjotgosal2489 Hi thanks for reply, Glitches like inbetween spikes or suddenly reduce time interval

@helios4.257 7 ай бұрын

Hello, we are working on an assignment related to gender recognition from voice. However, we want to extract values such as "mean frequency, standaty deviation ,spectral flattnes" from a person's voice using the data you use. How can we achieve this?