Undefined function error in Audio Toolbox and Deeplearning Toolbox

I am trying to run a pretrained network on speech command recognition demonstrated on this page:

https://www.mathworks.com/help/deeplearning/ug/deep-learning-speech-recognition.html

My code is here, it is simply a copy of what the page instructs:

load('commandNet.mat')
[x,fs] = audioread('stop_command.flac');
sound(x,fs)
auditorySpect = helperExtractAuditoryFeatures(x,fs);
command = classify(trainedNet,auditorySpect)

and I got these warnings and a error:

Warning: Unable to load instances of class weightedClassificationLayer into a heterogeneous array. The definition of

weightedClassificationLayer could be missing or contain an error. Default objects will be substituted.

Warning: While loading an object of class 'SeriesNetwork':

Error using 'predict' in Layer nnet.cnn.layer.MissingLayer. The function threw an error and could not be executed.

Undefined function 'helperExtractAuditoryFeatures' for input arguments of type 'double'.

Error in T2 (line 4)

auditorySpect = helperExtractAuditoryFeatures(x,fs);

Could any one tell why I got this error?

Answer 1

[Brian Hemmat]

Hi Yifan,

To run the example, you'll need to open the example using this command:

openExample('deeplearning_shared/DeepLearningSpeechRecognitionExample')

Alternatively, you can click the button on the top right of the example.

That command will open a copy of the example into a new location that includes all necessary helper files. You can step through the example from there.

HTH,

Brian

[Yifan Dong]

Thank you very much! I can run the exmaple now.