skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: B/LV Laboratory Accessibility Technology Adapted for Neurodiverse Chemistry Students
Text-to-speech technology is a common accommodation available for students with disabilities. Despite the ubiquitous nature of text-to-speech, this technology has not been explored in laboratory settings for neurodiverse college students. This study explores the adaptability of laboratory accessible text-to-speech technology (originally developed for blind/low vision (B/LV) students) for neurodiverse students. Students were asked to provide general feedback about the usability and effectiveness of the technology using Likert surveys. The students also answered open-ended questions about how the technology could be adapted to be more neurodiverse friendly. Overall, more than 50% of the students found the technology useful but had specific feedback about adaptations that could make it even more universal.  more » « less
Award ID(s):
2129912
PAR ID:
10518845
Author(s) / Creator(s):
Corporate Creator(s):
Publisher / Repository:
Journal of Science Education for Students with Disabilities
Date Published:
Journal Name:
Journal of Science Education for Students with Disabilities
Volume:
26
Issue:
1
ISSN:
1940-9923
Page Range / eLocation ID:
1 to 9
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. (, AERA Online Repository)
    [NAME] is an initiative aimed at supporting students with executive function (EF) disabilities through the use of augmented reality (AR). The use of a co-design process is central to its development, which involves collaborating with neurodiverse co-designers to ensure the tool meets the unique needs of this population (Spiel at al., 2022). By working closely with students from [NAME], design and development of this technology was consistently informed by the needs of the neurodiversity community. The co-design approach emphasized inclusivity and active participation, involving open dialogue, feedback sessions, and iterative design cycles. This process allowed the project team to refine the tool based on real-world usage and feedback. One of the main goals of [NAME] is to create an engaging and supportive user experience. By understanding the specific challenges faced by students with EF differences, such as ADHD, the team developed features that addressed these challenges directly. The AR interface was designed to be intuitive and interactive, helping students stay focused on their STEM related tasks. The tool uses machine learning algorithms to monitor students' attention and distractibility, providing feedback and adjusting prompts as needed. This adaptive feature is important for creating a supportive learning environment that evolves with the student’s progress (Ahmad, 2015). Personalized prompts and reminders will then be tailored to each student’s needs, providing timely support to help them stay on track. The co-design process empowers neurodiverse students by giving them a voice in the development of the tools they will use. By incorporating their feedback and insights, [NAME] ensures that the final product is both practical and empowering. This approach enhances the tool's effectiveness and fosters a sense of ownership and confidence among the students. The innovative co-design methodology used in [NAME] sets a precedent for future educational technologies. By demonstrating the value of inclusive design and the potential of AR in education, the project paves the way for more accessible and effective learning tools. The ultimate vision is for [NAME] is to serve as a model for scalable interventions that support a wide range of learners in both academic and workplace settings. The co-design features of [NAME] highlight the importance of collaboration, personalization, and adaptability in creating educational tools that meet the needs of neurodiverse students (Armstrong, 2012). By leveraging AR and involving the end-users in the design process, [NAME] aims to improve how students with EF disabilities engage with STEM learning. 
    more » « less
  2. ; ; ; ; ; ; (, Proc. Interspeech 2022)
    An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts written in that language without access to any transcribed speech. Developing such a system can significantly improve the availability of speech technology to languages without a large amount of parallel speech and text data. This paper proposes an unsupervised TTS system based on an alignment module that outputs pseudo-text and another synthesis module that uses pseudo-text for training and real text for inference. Our unsupervised system can achieve comparable performance to the supervised system in seven languages with about 10-20 hours of speech each. A careful study on the effect of text units and vocoders has also been conducted to better understand what factors may affect unsupervised TTS performance. The samples generated by our models can be found at https://cactuswiththoughts.github.io/UnsupTTS-Demo, and our code can be found at https://github.com/lwang114/UnsupTTS. 
    more » « less
  3. ; (, Thirteenth AAAI Symposium on Educational Advances in Artificial Intelligence)
    Neumann, M.; Virtue, P.; Guerzhoy, M. (Ed.)
    Children of all ages interact with speech recognition systems but are largely unaware of how they work. Teaching K-12 students to investigate how these systems employ phonological, syntactic, semantic, and cultural knowledge to resolve ambiguities in the audio signal can provide them a window on complex AI decision-making and also help them appreciate the richness and complexity of human language. We describe a browser-based tool for exploring the Google Web Speech API and a series of experiments students can engage in to measure what the service knows about language and the types of biases it exhibits. Middle school students taking an introductory AI elective were able to use the tool to explore Google’s knowledge of homophones and its ability to exploit context to disambiguate them. Older students could potentially conduct more comprehensive investigations, which we lay out here. This approach to investigating the power and limitations of speech technology through carefully designed experiments can also be applied to other AI application areas, such as face detection, object recognition, machine translation, or question answering. 
    more » « less
  4. ; (, Thirteenth AAAI Symposium on Educational Advances in Artificial Intelligence .)
    Children of all ages interact with speech recognition systems but are largely unaware of how they work. Teaching K-12 students to investigate how these systems employ phonolog- ical, syntactic, semantic, and cultural knowledge to resolve ambiguities in the audio signal can provide them a window on complex AI decision-making and also help them appreciate the richness and complexity of human language. We describe a browser-based tool for exploring the Google Web Speech API and a series of experiments students can engage in to measure what the service knows about language and the types of biases it exhibits. Middle school students taking an introductory AI elective were able to use the tool to explore Google’s knowledge of homophones and its ability to exploit context to disambiguate them. Older students could potentially conduct more comprehensive investigations, which we lay out here. This approach to investigating the power and limitations of speech technology through carefully designed experiments can also be applied to other AI application areas, such as face detection, object recognition, machine translation, or question answering. 
    more » « less
  5. ; (, Mindbrained bulletin)
    The last decade has seen an increasing shift away from deficit-based models of supporting students with disabilities. Such models focus on the weaknesses of individual students in an effort to correct the perceived weaknesses, with little attention paid to teach students how to identify and capitalize on their unique strengths. Recently , many educators have adopted more balanced approaches, including strength-based models that incorporate a student-centered approach to teaching that helps these students understand their strengths (Parsakia et al., 2022). Strength-based models highlight the importance of teaching students how to improve strong areas and capitalize on them in learning environments. In this article we share observations, particularly observations of parents about the strengths of their children, from a project at the University of Washington (UW) that aims to help neurodiverse learners prepare for and succeed in college. The project, Neuroscience for Neurodiverse Learners (NNL), provides hands-on experiences in neuroscience, networking opportunities , and resources to high school and early post-secondary students who identify as "neurodiverse" learners: those with academic challenges related to THINK TANK: Neurodiversity. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email