We’re rewarding the question askers & reputations are being recalculated! Read more.

Questions tagged [spectrogram]

A spectrogram is a time-varying spectral representation (forming an image) that shows how the spectral density of a signal varies with time.

Filter by
Sorted by
Tagged with
0
votes
0answers
7 views

Normalize a Mel-Spec over which axis?

I have to find out: how to normalize a Mel-spectrogram.(for mashine-learning purpose) However, I don't know which axis has to be transformed. The spectrogram S is of shape (m x n) where n are the ...
0
votes
1answer
39 views

Feature Extraction of Insect Sounds

First of all, forgive me if I sound stupid. I am still learning Audio Processing. So I am trying to make a machine learning model for detecting a specific insect through sound. Here is a sample raw ...
2
votes
1answer
88 views

How to interpret these MP3 spectrums?

Recently, I found I had this song duplicated in my music library, but when listening to them I noticed one version was of noticeably higher quality than the other despite both claiming to have a ...
0
votes
0answers
11 views

Power spectral density of surface roughness

I am currently working on understanding how visually and intuitively the power spectral density is the fourier transform of the autocorrelation of a signal. I was wondering if anyone had a good ...
0
votes
0answers
16 views

Some confusion about calculating spectrogram

I am new to DSP and i have a question because it is not the same as theory. I need to get spectrogram of wav file and feed it to CNN. I have used scipy.signal to get spectrogram. I know spectrogram ...
0
votes
1answer
37 views

Why does a strange frequency appear in this image?

Here is an image of a filter bank spectrograph, where the main signal is at 2.5kHz and the high signal is at 21.5khz, What is the high frequency signal? I doubt that birds can make frequencies above ...
1
vote
0answers
21 views

How to find the Pitch of a utterance using narrowband spectrogram

Can anyone tell me how to find the pitch of an utterance from it's narrow band spectrogram? I am pretty new to the speech processing domain so any help is appreciated. P.S. I need methods to estimate ...
0
votes
2answers
77 views

Fourier like spectral analysis with uneven intervals and redesigned DFT matrix

I intended to use a discrete Fourier transform (DFT) on a time series sampled at uneven intervals. What I did was to calculate a DFT matrix where the elements are the values at the uneven locations ...
1
vote
0answers
22 views

Bandpass Experiment: Weird graph! amplitude mismatch?

Why is this generic BP filter seem to magnifying amplitudes when I run it at lower sample rates? The bass range seems to 32 times louder at 1275 Hz (44.1 kHz / 32) than at 44.1kHz? Here is a graph of ...
8
votes
2answers
2k views

Converting mel spectrogram to spectrogram

I have a set of songs for which I extracted the STFT (Short-Time Fourier Transform) and used the magnitude spectrum $|S|$ to calculate the mel spectrogram by using a mel filterbank matrix $M$, so $X=\...
0
votes
0answers
20 views

Modified STFT resynthesis

This post is basically a follow-up to my recent question, which I asked here How to deal with phase incoherence issues after manipulating a signal in the frequency domain? In short, I'm modifying the ...
0
votes
1answer
40 views

Compensate for microphone?

I have trained a machine learning model to recognize a specific audio event from mel spectrograms, and it works pretty well on a hold-out test dataset. I now want to run the model on a device and feed ...
0
votes
1answer
532 views

Phoneme Clustering

My aim is to find cluster phonemes from a wav file. I would like to go through the following steps: I am calculating spectrogram. Calculate energy of each frame. Cluster the frames using k-means ...
1
vote
1answer
133 views

Continuous wavelet transform subsampling at lower frequencies?

I am not completely confident in my understanding of wavelet theory, but since I am currently in the process of creating a CWT scalogram tool, I have to ask: Is there a theorem allowing us to ...
0
votes
0answers
11 views

Fluctuations of spectral density estimates

I have seen in a few papers things like : or Without ever seeing the assumptions which are made, and of course no justifications. Does somebody know why it is a valid approximation to make ?
0
votes
4answers
147 views

What are some alternatives to Spectrogram charts? [closed]

Spectrogram renders of audio are limited in their representation of audio. For example, one could not use a Spectrogram to re-render the original audio. What are some alternatives to Spectrogram ...
1
vote
1answer
670 views

How can create a .wav bar based spectrogram on matlab?

How can I create a bar based spectrogram that updates as a .wav file is playing. This is commonly found in music players. Here is an example below: I am able to display a amplitude/frequency graph ...
1
vote
2answers
645 views

Quantify the difference between two audio spectrograms

I have two speech signals of the same length. They contain the exact same speech content but are recorded from two different microphones. I want to compare the differences between them. 1) Assuming ...
1
vote
1answer
44 views

Normalizing vectors to be the same size to retain PSD data

Context: PSD=periodogram(y) in MATLAB gives the PSD (power spectral density) estimate of a sound-source signal. I want to find the local maximum within 3 different ...
1
vote
1answer
4k views

Spectrogram, time vs frequency localization, and length of signal

So I'm having some trouble conceptually and am hoping somebody can clear something up for me. This is long and I apologize for that but I want to provide as much information as possible so that the ...
0
votes
1answer
614 views

Comparing band-pass filters and convolutional kernels?

I am currently working on extracting features for speech recognition purposes. I wanted to try an approach similar to MFCC features in which the center frequency of each band pass filters are placed ...
1
vote
1answer
515 views

Is the Auditory Spectrogram the same as the Magnitude Spectrogram?

This is in the context of speech signals. The magnitude spectrogram is computed by framing the signal into short time windows, applying a hamming (or similar) window, computing the fft over each ...
0
votes
1answer
91 views

High resolution spectrograms

I have a recorded audio signal that I would like to convert into spectrogram with the highest possible yield of information. The audio clips I am working with is about 30 ms long and contains ...
1
vote
0answers
25 views

how to reconstruct an phase information from the magnitude spectrogram

I need to recreate the phase of a spectogram of magnitude and when inverse fourier, that the sound is understandable and not pure noise Observe these softwares https://photosounder.com/ http://...
0
votes
1answer
343 views

how to create a harmonic mask from fundamental frequency?

Using an algorithm that gives the fundamental frequency across time, example https://www.mathworks.com/help/audio/ref/pitch.html (or some other one?) how would I then use that, to create a harmonic ...
1
vote
1answer
122 views

How can you 'perfectly' reconstruct phase for transients in a modified audio absolute spectrogram?

I am currently working on the absolute spectrogram of an input audio signal. I am using non-negative matrix factorization to separate out the rhythmic components (bass drum, snare drum and hi-hat) of ...
1
vote
2answers
96 views

Old style signal processing?

I am wondering if "an array of overlapping band-pass filters" it is 'mostly' equivalent to a Short-Time Fourier transform. See this (figure down), where $s(t)$ is the signal; LPF a second-order low-...
0
votes
2answers
49 views

Augmentation for EEG signal classification using Deep Learning

Augmentation is a technique that we use in deep learning for expanding the training dataset. It includes different ways of modifying an image and adding it to the training dataset. My question is if ...
0
votes
2answers
70 views

Phase information of a signal when creating a spectrogram

Sorry for the uninformed question but I need some help understanding this. I'm trying to understand what phase information is and it would be very helpful if someone could correct my understanding of ...
0
votes
0answers
28 views

Python mixing, filtering, and decimation. I'm a rookie!

Background: I have a spectrogram of window length 256 time frames and window width 1024 frequency bins. It initially took IQ using 10*log_10(magnitude) to output this spectrogram with window overlap ...
0
votes
3answers
69 views

Using different algorithms/formulas to create spectrograms

On the internet, I have seen people use Matplotlib/Python and short-time fourier transformations to create spectrograms. Are their other formula/algorithms to create spectrograms? And are they ...
0
votes
1answer
104 views

Spectrogram Time Resolution with Overlap

I understand that the time resolution of a spectrogram with no overlap is the sampling frequency divided by the window length. How does this change with, say, 50% overlap? Does this double the time ...
0
votes
0answers
30 views

Spectrogram using SciPy - bad scaling of the timeline [duplicate]

I have a real value signal which has 197 samples (every 1 second). I made its spectrogram using the SciPy library: ...
0
votes
0answers
9 views

Why can ARSS not recreate audio from a spectrogram without sounding muffled?

Why do ARSS and all audio to spectrogram then back to audio program's create audio files that sound muffled? I know their is some physics and math with the short-time Fourier transform and etc. I ...
1
vote
1answer
66 views

Finding where signal is showing some (unknown) periodicity

I have readings of the vertical displacement of someone over time, as in the picture below: At some points in time, the person will be exercising or jumping up & down, creating more or less ...
1
vote
0answers
27 views

When do phases not exist for spectrograms?

I have been reading a paper on the "Single pass spectrogram inversion" and I came across this in the Introduction part. In many applications, the analysis and modification of the Short-Time ...
0
votes
0answers
35 views

Optimizing Spectrogram Parameters

I'm looking for references that explain the trade-offs between more averages with shorter fft sizes or longer fft sizes with fewer averages when generating a spectrogram to perform energy detection of ...
2
votes
1answer
279 views

Spectrogram of a single tone complex signal has two dark lines?

I am trying to plot the spectrogram of a complex signal I generated. I have written code to generate this signal and plot the spectrogram. It works. However I see that there are two dark lines present ...
0
votes
1answer
106 views

Spectrogram power/magnitude normalization in analogy with image intensity normalization

In analogy with the 8-bit grayscale image color depth, in which the intensity of a sample pixel is normalized to a value between 0 and 255 by taking into account the minimum and maximum intensities ...
1
vote
2answers
206 views

audio spectrogram normalization

I am performing language classification from audio signals using mel-spectrograms as my inputs for a ResNet. It works well as long as all of my audio data from different languages is from the same ...
0
votes
1answer
245 views

How to convert a spectrogram back to a signal [duplicate]

I'm converting a signal to a spectrogram, manipulating that (nonlinear stuff), and then want to use the modified audio signal. I can make it so the segments are not overlapping, but am unsure how to ...
3
votes
3answers
3k views

Why do we get ripples in the frequency spectrum of a chirp, and how do I remove it?

The ripples in the amplitude spectrum of a linear spectrum is undesirable. I desire to obtain a flat spectrum response. Hence, how can I remove these ripples? Also, which factors (like time bandwidth ...
0
votes
0answers
21 views

Spectrogram of chirp sequence radar signals

I am confused as to whether SFFT makes sense to process chirp sequence signals. The radar fires up a sequence of 100 linear ramps with that are only interrupted by the very short period in which the ...
0
votes
0answers
21 views

finding harmonics from fundamental

https://s3.amazonaws.com/izotopedownloads/docs/rx700/en/interactive-tools/index.html#selection-tools From the above link, under the "Magic Wand" tool description, how does that algorithm work? In RX,...
3
votes
2answers
1k views

What is the most precise frequency analysis spectrography algorythm?

Everyone uses Fast Fourier Transform, which is fast at the detriment of precision. The input audio has sample accuracy and the FFT has 1/64 sample accuracy. What algorithms can output high resolution ...
0
votes
0answers
296 views

How to Extract frequency bands from Short-time Fourier Transform?

I am reproducing the results reported by the author in a research paper. In which he takes the STFT of EEG signals. The input data has a shape of (1 X500) and I used Scipy library built-in function to ...
0
votes
1answer
61 views

Extracting audio from picture of time-domain signal

I saw this nifty art thing where they dress up the time-domain audio signal in some pretty way. https://www.etsy.com/ArtbloxShop/listing/621561709/sound-wave-art-custom-soundwave-print My question is ...
0
votes
1answer
57 views

How to classify the movement type of a target into two categories(direct motion or else) by using a doppler radar?

How to classify the movement type of a target just into two categories(one is direct motion which is almost straight line movement and the other is anything else) by using a doppler radar with a ...
0
votes
1answer
1k views

How to go from wav file to spectrogram back to wav file in python?

Close to this question but different : Wav To Spectrogram, Back To Wav I already posted this on StackOverflow(https://stackoverflow.com/questions/54743968/how-to-go-from-wav-file-to-spectrogram-back-...
0
votes
0answers
352 views

Recover Audio from Spectrogram Image

I have applied transformation(Constant Q Transformation) to my audio time domain signal, this gives me Frequency vs Time representation. Now, the CQT values consists of complex values(84*260), but ...