Binary classifier for identification of stammering instances in Hindi speech data

In this research paper we show results from our experiments on creating a binary classifier for stammering identification in Hindi speech data. We train several Sequential CNN models with parametric adjustments such as color, image size, and training data shape changes to tweak classification performance. Our experimental pipeline converts speech samples into spectrograms using Librosa, and trains the Sequential CNN classifier on the image data using TensorFlow Lite. Our classification models achieve more than 95% accuracy in this classification task. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.