I want to use multiple frames for prediction with Live Audio

Hello Matlab team,

I am using this example to work with my audio data set https://www.mathworks.com/matlabcentral/fileexchange/74611-fault-detection-using-deep-learning-classification#examples_tab dataset is trained

I made a live application which uses 44.1Khz as a sample rate and 22Khz frame is used for classification of audio.

I want to give multiple frames to my model, forexample now data of half second is used for classification but i want to give 2 or 3 seconds of data to my model for classification.

Can you guide me or help me with that?

Regards,

Arslan Munaim