Respondida
What is the default normalization in plot of stft function in Short-time Fourier transform
Hi Muhammad, I beleive the plot you get with STFT uses log, so 20*log10(abs(S)+eps) is plotted.

casi 2 años hace | 1

| aceptada

Respondida
Saving images quickly for huge datasets
Hi Joenam, A couple of things I noticed in your code: 1) You rely on melSpectrogram to generate a plot for you, which is fin...

alrededor de 2 años hace | 1

Respondida
Trying to convert whole folder into spectrograms
Hi Justine, consider using an audioDatastore to do this. then you don't have to write the for loop. for example: % This audioDa...

alrededor de 2 años hace | 0

| aceptada

Respondida
VGGishPreprocess not accepting input
Hi Joshua, First, sorry we had a local funtion name with the same name as a function we ship. We are fixing this. The functi...

alrededor de 2 años hace | 1

| aceptada

Respondida
Need help with Volume Slider GUI
Hi Nikos, Consider using audioDeviceWriter to play the audio, and dsp.AudioFileReader to read from the audio file. You do not...

alrededor de 2 años hace | 0

| aceptada

Respondida
Speech To Text SAPI Offine mode
Hi Nikos, You can try out wav2vec 2.0. You can find a MATLAB implementation here: https://github.com/matlab-deep-learning/wav2...

alrededor de 2 años hace | 1

| aceptada

Respondida
Audio Files in a Triggered Subsystem?
Hi Benjamin, You can't use this audio block in a triggered subsystem. You can try an enabled subsystem though. Both From Multim...

alrededor de 2 años hace | 0

Respondida
Howto explore large collection of audio files with custom parameters display beside time and frequency domain graphs ?
Hi Robert, audioDatastore will help you manage a large number files. The signal analyzer app will help you visualize files, a...

alrededor de 2 años hace | 0

Respondida
Recorded Audio is Shorter than Expected
Hi Xiwen, I suspect the scope is taking a long time to set up the first time you call it. Consider adding this code outside...

alrededor de 2 años hace | 0

| aceptada

Respondida
How to extract VGGish features from audio files shorter than 1s?
Hi Robert-Valentin, The VGGIsh network accepts auditory spectrograms that correspond to roughly one second of audio, so you do ...

alrededor de 2 años hace | 1

Respondida
How can I change the database and pretrained generator ?
Hi Aseel, The example starts off by showcasing the pretrained network. The network was trained to produce drum-like sounds. If ...

alrededor de 2 años hace | 0

Respondida
For a network with 1 inputs and 1 output, the datastore read function must return a cell array with 2 columns, but it returns an cell array with 1 columns.
Hi Gudimalla, The training process typically expects a pair from the datastore: For classification problems, it expects a mel s...

alrededor de 2 años hace | 1

| aceptada

Respondida
what should be the constraint on window length in function melspectrogram?
Hi Krishna, This looks fine. Make sure that your input x is a column vector, not a row vector. The function treats each column ...

más de 2 años hace | 0

| aceptada

Respondida
Need continuous sound played from buffer A then B. I fill B while A is playing, then visa versa.
Hi David, For real-time sound applications, you should use audioDeviceWriter: https://www.mathworks.com/help/audio/ref/audiode...

más de 2 años hace | 0

| aceptada

Respondida
"audioread" multiple audio files in a folder
For future reference, I recommend you use audioDatastore: https://www.mathworks.com/help/audio/ref/audiodatastore.html You won...

más de 2 años hace | 0

Respondida
Get sample rate in a Matlab function block in Simulink
Hi Glenn, I've accomplished this in the past using a probe block: https://www.mathworks.com/help/simulink/slref/probe.html Th...

más de 2 años hace | 0

Respondida
Is there a function or a way to write/read bit by bit to/from a buffer in MATLAB?
Hi An, Maybe dsp.AsyncBuffer works for you? b = dsp.AsyncBuffer; write(b,1); % write the number 1 to the buffer write(b,2);...

más de 2 años hace | 0

| aceptada

Respondida
Iterate speech frames through all the audio file in the folder
Hi Camille, The function mfcc breaks the signal into frames for you, so you do not need to perform the frame processing yoursel...

más de 2 años hace | 0

| aceptada

Respondida
how to separate an audio file based on different speakers
Hi Andrei, Speaker diarization is one way to address it. Check out this example: https://www.mathworks.com/help/audio/ug/spe...

más de 2 años hace | 0

Respondida
How do I connect my ASIO sound card to Matlab??
Hi Wilmer, You should be able to use the ASIO sound card with the objects in Audio toolbox: audioDeviceWriter, audioDeviceRead...

más de 2 años hace | 0

Respondida
I am missing the test signal "WashingMachine-16-8-mono-200secs.mp3" from the denoise example.
We've changed this example over the releases, but everything should work as long as the demo you're reading matches with your MA...

más de 2 años hace | 0

| aceptada

Respondida
How to create and train a LSTM network for audio denoising in MATLAB
This example does not use LSTMs, but it should be useful: https://www.mathworks.com/help/deeplearning/ug/denoise-speech-using-d...

más de 2 años hace | 0

| aceptada

Respondida
How to implement Trained CNN for audio denoising in simulink
Hi Arvinda, This is possible. You can leverage your trained network by using one of these Simulink blocks (Image Classifier, Pr...

más de 2 años hace | 0

Respondida
How to create a MATLAB code for generating audio sine wave signal of frequency ranges from 1Hz to 15kHz and plot it on real time.
Zafar, you can achieve this with audioOscillator and timescope. Here is an example. % Generate and visualize a sine wave with v...

más de 2 años hace | 0

Respondida
spl_meter function output vlaue difference
Hi Hamin, splMeter contains filters that remember the previous output, i.e. it has states. You should not expect the same input...

más de 2 años hace | 0

| aceptada

Respondida
How to read datastore from specified position?
Hi Neal, Here is one way to read files from a custom position: adsSub = subset(adsTest,20:40); allSignals = readall(adsSub)...

más de 2 años hace | 0

Respondida
Is there a possibility to scale the x-axis of the splMeter Window?
Hi Bjorn, I noticed that you set TimeSpanSource to true on the scope, but did not change the actual time span value. Maybe that...

más de 2 años hace | 0

Respondida
Use StretchAudio in realtime
Hi youngz, I suggest you use audioTimeScaler: https://www.mathworks.com/help/audio/ref/audiotimescaler-system-object.html T...

más de 2 años hace | 0

Respondida
Help trouble shooting my code that uses a voice recognition system to identify fruits in real time
Hi Elliot, That file (weightedClassificationLayer) is not on path by default. It is attached to the example. From the doc, op...

más de 2 años hace | 0

Respondida
Finding multiple fundamental frequencies using the pitch function
Hi Heeje, You've specified WindowLength as size(1,wsize). I suspect you mean wsize. The pitch function accepts a Range proper...

casi 3 años hace | 1