AI-enhanced Speech and Voice Recognition Tools: Improving Communication for Children with Apraxia and Stuttering

Authors

  • Swarasai Mulagari Evergreen Valley High School
  • Ms. Miao East Side Union High School District

DOI:

https://doi.org/10.47611/jsrhs.v14i1.10360

Keywords:

Apraxia, Stuttering, Speech Recognition, Voice Recognition, Artificial Intelligence, Machine Learning, Assistive Technologies

Abstract

This paper explores the remarkable advancements in Artificial Intelligence (AI)-driven speech and voice recognition technologies, focusing on their transformative role in improving communication for children with speech disabilities such as apraxia and stuttering. These advancements represent a new frontier in assistive technology, with AI significantly enhancing the accuracy, adaptability, and effectiveness of speech recognition systems. We examine how AI-powered tools are being utilized to improve speech clarity, enable more effective communication, and support personalized therapy interventions tailored to individual needs. The integration of deep learning, machine learning, and natural language processing has proven instrumental in overcoming the challenges posed by traditional therapeutic methods, offering more precise and dynamic solutions. Additionally, this paper reviews the current landscape of AI-based tools, providing insights into their impact on therapy outcomes and quality of life for affected children. The discussion extends to the ethical considerations, such as data privacy, inclusivity, and algorithmic bias, ensuring the responsible development of these technologies. Finally, we explore the future potential of AI-driven solutions, highlighting their promise in creating more inclusive, accessible, and effective communication support systems for children with speech disabilities worldwide.

Downloads

Download data is not yet available.

References or Bibliography

Shahin, M., Ahmed, B., Parnandi, A., McKechnie, J., & Ballard, K. J. (2015). Tabby Talks: An automated tool for the assessment of childhood apraxia of speech. Speech Communication, 70, 49–64. https://www.sciencedirect.com/science/article/abs/pii/S0167639315000382?via%3Dihub

Kumar, B., Singh, A. V.., & Agarwal, P.. (2022). A Novel Approach for Speech to Text Recognition System Using Hidden Markov Model. International Journal on Recent and Innovation Trends in Computing and Communication, 10(12), 181–190.

Amberkar, A., Awasarmol, P., Deshmukh, G., & Dave, P. (2018). Speech recognition using recurrent neural networks. In 2018 International Conference on Current Trends Toward Converging Technologies (Coimbatore: IEEE).

DOI: 10.1109/97.736233

Google Cloud Speech-to-Text (2020). Google Cloud Speech API documentation.

Available at: https://cloud.google.com/speech-to-text/docs

Voiceitt (2021). Speech recognition for non-standard speech. Voiceitt https://www.voiceitt.com/

LumenVox (2022): AI Speech Recognition & Voice Authentication

World Health Organization (WHO) https://www.who.int/

American Speech-Language-Hearing Association (ASHA) https://www.asha.org/

Published

02-28-2025

How to Cite

Mulagari, S., & Miao, I. (2025). AI-enhanced Speech and Voice Recognition Tools: Improving Communication for Children with Apraxia and Stuttering. Journal of Student Research, 14(1). https://doi.org/10.47611/jsrhs.v14i1.10360

Issue

Section

HS Review Projects