Logo image
LipTalk: Deployable Context-Aware LipTalk for Clinical Communication
Conference proceeding

LipTalk: Deployable Context-Aware LipTalk for Clinical Communication

Nirase Fathima Abubacker, Cindy Koh Xin Yi and Md Baharul Islam
IEEE Conference on Systems, Process & Control (Print), pp.263-268
2025 IEEE 13th Conference on Systems, Process & Control (ICSPC) (Melaka, Malaysia, 12-05-2025–12-06-2025)
12-05-2025

Abstract

Accuracy context fusion Decoding Error analysis facial expression recognition Facial expressions healthcare communication Lip reading Lips Medical services mobile health Pipelines Prototypes Speech recognition visual speech recognition Visualization Autism
Patients who cannot vocalize often struggle to convey symptoms during clinical encounters, increasing the risk of misunderstanding and delayed care. We present LipTalk, a mobile system that combines LipTalk (visual speech recognition) with facial-expression analysis to support patient/clinician communication. The pipeline couples a 3DCNN/BiLSTM lipreader with CTC decoding and a lightweight 2DCNN affect classifier, deployed via an Android client with server-side inference. On the publicly available datasets, our LipTalk achieves 54.8% character accuracy (CAR), 22.9% character error rate (CER), 55.6% word accuracy (WAR), and 46.2% word error rate (WER); the affect module reaches 64.1% test accuracy. A simple context-aware re-ranking yields a +2.3pp gain in WAR over lip-only decoding. Prototype tests indicate sub-second end-to-end latency for short utterances, suggesting feasibility for bedside use while motivating clinical data collection and broader evaluation.
url
Link to conference paper.View

Related links

Metrics

1 Record Views

Details

Logo image