- Conference Article
- 10.1109/dicta68720.2025.11302499
Understanding Non-Verbal Vocalizations from Minimally-Verbal Autistic Individuals: A Transfer Learning Approach
- Dec 03, 2025
- Anirudh Atmakuru + 6 more +6
Autism Spectrum Disorder (ASD) often includes challenges in verbal communication, particularly for minimally verbal (mv*) individuals. Mv* individuals with ASD often find it difficult to communicate with people since their vocalizations are highly personalized and often non-verbal, making it extremely difficult for people to understand their needs. Recent advances in machine learning and deep learning have made it possible for researchers to explore new avenues and provide personalized care for individuals with ASD. This research explores transfer learning and Mel spectrograms to classify nonverbal vocalizations from <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{mv}^{*}$</tex> ASD individuals, aiming to improve understanding and communication. We conduct three experiments to verify the robustness and generalizability of our approach in different setups. Using a dataset of 7077 vocalizations from eight mv* individuals collected from noisy, real-world settings, we convert the audio signals to Mel spectrograms and evaluate six transfer learning models and a custom convolutional neural network model. Our experiments demonstrated that DenseNet161, ResNet101, and VGG19, particularly when combined in an ensemble, effectively classify vocalizations into six categories: self-talk, frustration, delight, dysregulation, social, and request. Results suggest that this ensemble achieves state-of-the-art performance with an F1 score of 0.79, outperforming traditional machine learning methods and highlighting the potential of artificial intelligence in enhancing care for mv* ASD individuals.
Read more