Comuniqa : Exploring Large Language Models for improving speaking skills

TL;DR

Cominiqa addresses the challenge of scalable English speaking skill enhancement for non-native speakers by deploying an LLM based feedback system integrated with multimodal speech analysis. The study compares AI only, human expert coaching, and a hybrid AI plus expert approach in a two week protocol with 34 participants, examining engagement, scores and qualitative perceptions. Findings indicate that while LLM based feedback provides accurate, comprehensive assessments, it lacks human level cognition and empathy seen in expert coaching, yet a hybrid model can offer practical benefits for accessibility and motivation. The work demonstrates a path toward SDG 4 by enabling quality education through scalable tools that broaden access to speaking practice, especially where expert resources are scarce.

Abstract

In this paper, we investigate the potential of Large Language Models (LLMs) to improve English speaking skills. This is particularly relevant in countries like India, where English is crucial for academic, professional, and personal communication but remains a non-native language for many. Traditional methods for enhancing speaking skills often rely on human experts, which can be limited in terms of scalability, accessibility, and affordability. Recent advancements in Artificial Intelligence (AI) offer promising solutions to overcome these limitations. We propose Comuniqa, a novel LLM-based system designed to enhance English speaking skills. We adopt a human-centric evaluation approach, comparing Comuniqa with the feedback and instructions provided by human experts. In our evaluation, we divide the participants in three groups: those who use LLM-based system for improving speaking skills, those guided by human experts for the same task and those who utilize both the LLM-based system as well as the human experts. Using surveys, interviews, and actual study sessions, we provide a detailed perspective on the effectiveness of different learning modalities. Our preliminary findings suggest that while LLM-based systems have commendable accuracy, they lack human-level cognitive capabilities, both in terms of accuracy and empathy. Nevertheless, Comuniqa represents a significant step towards achieving Sustainable Development Goal 4: Quality Education by providing a valuable learning tool for individuals who may not have access to human experts for improving their speaking skills.

Figures (15)

• Figure 1: Block level diagram of the system infrastructure
• Figure 2: Report Screen
• Figure 3: Practice Screen
• Figure 4: Home Screen
• Figure 5: Coherence