Skip to main content
Commonmark migration
Source Link

I'm trying to understand the methodology from section 4 in this report about audio classification but I have some trouble understanding how they pre-process the data (dsp is not my area).

  • $30$ seconds audio clips are available, sampled at $22050\textrm{ samples/s}$.
  • The STFT is computed "on $2048$ sample windows at a frame rate of $31.25\textrm{ frames/s}$"

Somehow this results in spectrograms of size $149\times 149$ which are then feeded to a neural network.

  • Does each spectrogram cover $2048$ samples of the audio clip?

    Does each spectrogram cover $2048$ samples of the audio clip?

  • If so, is then $149$ the number of segments that we divide each spectrogram in?

    If so, is then $149$ the number of segments that we divide each spectrogram in?

  • So that $2048/149 = 13.745$ is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

    So that $2048/149 = 13.745$ is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

    To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be $22050/31.25 = 705.6 \textrm{ samples}$, is that correct? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be $22050/31.25 = 705.6 \textrm{ samples}$, is that correct? How can this be a non-integer?

I'm trying to understand the methodology from section 4 in this report about audio classification but I have some trouble understanding how they pre-process the data (dsp is not my area).

  • $30$ seconds audio clips are available, sampled at $22050\textrm{ samples/s}$.
  • The STFT is computed "on $2048$ sample windows at a frame rate of $31.25\textrm{ frames/s}$"

Somehow this results in spectrograms of size $149\times 149$ which are then feeded to a neural network.

  • Does each spectrogram cover $2048$ samples of the audio clip?
  • If so, is then $149$ the number of segments that we divide each spectrogram in?
  • So that $2048/149 = 13.745$ is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be $22050/31.25 = 705.6 \textrm{ samples}$, is that correct? How can this be a non-integer?

I'm trying to understand the methodology from section 4 in this report about audio classification but I have some trouble understanding how they pre-process the data (dsp is not my area).

  • $30$ seconds audio clips are available, sampled at $22050\textrm{ samples/s}$.
  • The STFT is computed "on $2048$ sample windows at a frame rate of $31.25\textrm{ frames/s}$"

Somehow this results in spectrograms of size $149\times 149$ which are then feeded to a neural network.

  • Does each spectrogram cover $2048$ samples of the audio clip?

  • If so, is then $149$ the number of segments that we divide each spectrogram in?

  • So that $2048/149 = 13.745$ is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

    To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be $22050/31.25 = 705.6 \textrm{ samples}$, is that correct? How can this be a non-integer?

I'm trying to understand the methodology from a report (sectionsection 4 in herethis report) about audio classification but iI have some trouble understanding how they pre-process the data (dsp is not my area).

  • 30s$30$ seconds audio clips are available, sampled at 22050 samples/s$22050\textrm{ samples/s}$.
  • The STFT is computed "on 2048 sample windows at a frame rate of 31.25 FPS""on $2048$ sample windows at a frame rate of $31.25\textrm{ frames/s}$"

Somehow this results in spectrograms of size 149x149$149\times 149$ which are then feeded to a neural network. Does each spectrogram cover 2048 samples of the audio clip? If so, is then 149 the number of segments that we divide each spectrogram in? So that 2048/149 = 13.745 is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

  • Does each spectrogram cover $2048$ samples of the audio clip?
  • If so, is then $149$ the number of segments that we divide each spectrogram in?
  • So that $2048/149 = 13.745$ is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be 22050/31.25 = 705.6 samples$22050/31.25 = 705.6 \textrm{ samples}$, is that correct? How can this be a non-integer?

I'm trying to understand the methodology from a report (section 4 here) about audio classification but i have some trouble understanding how they pre-process the data (dsp is not my area)

  • 30s audio clips are available, sampled at 22050 samples/s.
  • The STFT is computed "on 2048 sample windows at a frame rate of 31.25 FPS"

Somehow this results in spectrograms of size 149x149 which are then feeded to a neural network. Does each spectrogram cover 2048 samples of the audio clip? If so, is then 149 the number of segments that we divide each spectrogram in? So that 2048/149 = 13.745 is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be 22050/31.25 = 705.6 samples, is that correct? How can this be a non-integer?

I'm trying to understand the methodology from section 4 in this report about audio classification but I have some trouble understanding how they pre-process the data (dsp is not my area).

  • $30$ seconds audio clips are available, sampled at $22050\textrm{ samples/s}$.
  • The STFT is computed "on $2048$ sample windows at a frame rate of $31.25\textrm{ frames/s}$"

Somehow this results in spectrograms of size $149\times 149$ which are then feeded to a neural network.

  • Does each spectrogram cover $2048$ samples of the audio clip?
  • If so, is then $149$ the number of segments that we divide each spectrogram in?
  • So that $2048/149 = 13.745$ is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be $22050/31.25 = 705.6 \textrm{ samples}$, is that correct? How can this be a non-integer?

added 131 characters in body
Source Link

I'm trying to understand the methodology from a report (section 4 here) about audio classification but i have some trouble understanding how they pre-process the data (dsp is not my area)

  • 30s audio clips are available, sampled at 22050 samples/s.
  • The STFT is computed "on 2048 sample windows at a frame rate of 31.25 FPS"

Somehow this results in spectrograms of size 149x149 which are then feeded to a neural network. Does each spectrogram cover 2048 samples of the audio clip? If so, is then 149 the number of segments that we divide each spectrogram in? So that 2048/149 = 13.745 is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be 22050/31.25 = 705.6 samples, is that correct? How can this be a non-integer?

I'm trying to understand the methodology from a report about audio classification but i have some trouble understanding how they pre-process the data (dsp is not my area)

  • 30s audio clips are available, sampled at 22050 samples/s.
  • The STFT is computed "on 2048 sample windows at a frame rate of 31.25 FPS"

Somehow this results in spectrograms of size 149x149 which are then feeded to a neural network. Does each spectrogram cover 2048 samples of the audio clip? If so, is then 149 the number of segments that we divide each spectrogram in? So that 2048/149 = 13.745 is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be 22050/31.25 = 705.6 samples, is that correct? How can this be a non-integer?

I'm trying to understand the methodology from a report (section 4 here) about audio classification but i have some trouble understanding how they pre-process the data (dsp is not my area)

  • 30s audio clips are available, sampled at 22050 samples/s.
  • The STFT is computed "on 2048 sample windows at a frame rate of 31.25 FPS"

Somehow this results in spectrograms of size 149x149 which are then feeded to a neural network. Does each spectrogram cover 2048 samples of the audio clip? If so, is then 149 the number of segments that we divide each spectrogram in? So that 2048/149 = 13.745 is the number of samples that we use for computing the DFT in each segment? How can this be a non-integer?

To my understanding the frame rate is about how much overlap there are between windows, in this case the overlap would be 22050/31.25 = 705.6 samples, is that correct? How can this be a non-integer?

Source Link
Loading