Fluenzic: An English Enchancement Platform

With artificial intelligence becoming more common in education, there's a growing need for tools that make learning English more interactive and personalized. In this paper, we propose Fluenzic, a platform that unifies speaking, writing, and vocabulary practice into one seamless learning experience. Unlike many existing tools that isolate these skills, Fluenzic integrates them through a unified design. It uses speech recognition and natural language processing to provide learners with instant feedback during speaking tasks, while GPT-4 supports grammar and sentence structure analysis. The platform reviews user sentence submissions and offers helpful grammar and tone suggestions, along with simple explanations to make learning easier. Vocabulary building is made more engaging through synonym-based games and quizzes. In quiet environments, our speech recognition achieves about <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{9 0 - 9 5}$</tex> percent accuracy, and in noisy places like classrooms, it usually works <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$70-85$</tex> percent of the time, depending on mic quality, background noise, and accents (based on existing benchmarks of the speech-to-text engine we use). Fluenzic shows how AI can be used to make a practical, easy, and engaging tool for everyday English learning.

Authors

Institutions

Publication Details

Published
2025-07-18
DOI
https://doi.org/10.1109/accthpa65749.2025.11168753
Primary Topic
Natural Language Processing Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Fluenzic: An English Enchancement Platform

Hema Krishnan, P A Fahmitha, Irine Theresa Antony, Eveline Jeson et al.
Natural Language Processing Techniques
article

Fluenzic: An English Enchancement Platform

Hema Krishnan, P A Fahmitha, Irine Theresa Antony, Eveline Jeson, Merin Joe
article en

Abstract

With artificial intelligence becoming more common in education, there's a growing need for tools that make learning English more interactive and personalized. In this paper, we propose Fluenzic, a platform that unifies speaking, writing, and vocabulary practice into one seamless learning experience. Unlike many existing tools that isolate these skills, Fluenzic integrates them through a unified design. It uses speech recognition and natural language processing to provide learners with instant feedback during speaking tasks, while GPT-4 supports grammar and sentence structure analysis. The platform reviews user sentence submissions and offers helpful grammar and tone suggestions, along with simple explanations to make learning easier. Vocabulary building is made more engaging through synonym-based games and quizzes. In quiet environments, our speech recognition achieves about <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{9 0 - 9 5}$</tex> percent accuracy, and in noisy places like classrooms, it usually works <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$70-85$</tex> percent of the time, depending on mic quality, background noise, and accents (based on existing benchmarks of the speech-to-text engine we use). Fluenzic shows how AI can be used to make a practical, easy, and engaging tool for everyday English learning.

Cochin University of Science and Technology (IN)
Openalex Percentile: Top 86%
Natural Language Processing Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.