Deep Learning Speech Recognition Example, Problem with designAuditoryFilterBank

Hi,

I am trying to run the Deep Learning Speech Recognition Example (see link: https://www.mathworks.com/help/deeplearning/examples/deep-learning-speech-recognition.html) and I am having a proble with designAuditoryFilterBank. The error that I am getting is: "Undefined function or variable 'designAuditoryFilterBank'."

I check to see if I have Audio toolbox installed and I do....

Answer 1

[Steven Lord]

If you look at the end of the documentation page for the designAuditoryFilterBank function it says that this function was introduced in release R2019b. I suspect you're using an older release.

The online documentation is for the current release (right now that is release R2019b) so if you're using an older release you might want to check when the function you're trying to use was introduced, or check the documentation included as part of your local installation.

[Katarina Vuckovic]

Thanks, I am using 2019a. Is there an alternative that I can use in 2019a version? I would hate to reinstall everything.

Answer 2

[jibrahim]

Hi Katarina,

Here is the R2019a version of the example:

https://www.mathworks.com/help/releases/R2019a/audio/examples/Speech-Command-Recognition-Using-Deep-Learning.html

If you have R2019a, you should have access to the source code. That version of the demo uses the function melSpectrogram to generate the auditory spectrograms.