Background of the study
AI‑driven text‑to‑speech (TTS) applications convert written text into spoken audio using neural network‑based speech synthesis, enhancing accessibility for users with visual impairments, learning disabilities, or literacy challenges (Perez, 2023). Modern TTS systems offer natural‑sounding voices and customizable reading speeds, making digital collections more inclusive (Khan, 2024). At Edo State Polytechnic Library in Usen, an AI TTS plugin was integrated into the digital repository and online catalog to support diverse learner needs (Eze, 2025). While initial feedback highlights improved access to e‑books and journals, systematic evaluation of user satisfaction, comprehension outcomes, and technical usability has not been conducted. Factors such as language support, pronunciation accuracy for technical terminology, and interface design influence TTS effectiveness in academic contexts.
Statement of the problem
Despite TTS availability, users at Usen Library report occasional mispronunciations of discipline‑specific terms and difficulty navigating TTS controls, limiting the tool’s accessibility benefits. Without empirical data on application performance and user experiences, library staff cannot optimize TTS settings or provide targeted support to maximize inclusive access.
Objectives of the study
To evaluate pronunciation accuracy and intelligibility of AI TTS for academic texts.
To assess user satisfaction, comprehension, and engagement with TTS‑enabled resources.
To identify technical and training requirements for effective TTS implementation.
Research questions
How accurately does AI TTS render specialized academic vocabulary?
What impact does TTS use have on users’ comprehension and study efficiency?
What interface and support features improve user adoption of TTS applications?
Significance of the study
Findings will guide library technologists and accessibility coordinators in customizing TTS voices, improving user interfaces, and designing training sessions that empower all patrons—particularly those with print disabilities—to engage fully with digital resources at Usen Library.
Scope and limitations of the study
This study focuses on AI‑driven TTS applications within the digital services of Edo State Polytechnic Library, Usen. It excludes in‑person assistive devices and non‑digital materials. Limitations include variation in users’ hearing abilities and TTS engine updates.
Definitions of terms
Text‑to‑speech (TTS): AI technology that synthesizes spoken audio from text input.
Intelligibility: The clarity and comprehensibility of synthesized speech.
Accessibility coordinator: Library staff responsible for implementing services that support users with disabilities.
Background of the Study
Knowledge-sharing networks are critical for enhancing collaborative research and disseminating acad...
Background of the study:
Video marketing has revolutionized how brands communicate their stories, enabling a dynamic intera...
Background of the Study
Maternal healthcare is a critical component of healthcare systems, and access t...
Background of the Study
Course registration is a critical aspect of university management, where students select the course...
Waterborne diseases are a major public health issue in many parts of Nigeria,...
Social support plays a critical role in promoting mental health, particularly...
BACKGROUND OF THE STUDY
In recent times, there has been a high level of unprecedented insecurity across...
ABSTRACT
The mass media may have a crucial role in either reinforcing, or challenging such inequalities. Television, rad...
ABSTRACT
The Lomb-Scargle discrete Fourier transform (LSDFT) is a fairly popular technique for analyzing time series within the astronomy...
Background of the Study
International legal norms have increasingly influenced domestic legal frameworks, raising important...