# Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS

arXiv: https://arxiv.org/abs/2609.28988 · HTML: https://mlsanity.com/paper/2609.28988/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [End-to-end Audio-visual Speech Recognition with Conformers](https://mlsanity.com/paper/2102.06657/) (2021)
- [Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels](https://mlsanity.com/paper/2303.14307/) (2023)
- [SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision](https://mlsanity.com/paper/2303.17200/) (2023)
- [Speaker-adaptive Lip Reading with User-dependent Padding](https://mlsanity.com/paper/2208.04498/) (2022)
- [Towards Pose-invariant Lip-Reading](https://mlsanity.com/paper/1911.06095/) (2019)
- [VALLR: Visual ASR Language Model for Lip Reading](https://mlsanity.com/paper/2503.21408/) (2025)
- [Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition](https://mlsanity.com/paper/2505.22251/) (2025)
- [End-to-End Multi-View Lipreading](https://mlsanity.com/paper/1709.00443/) (2017)
- [Visual-Only Recognition of Normal, Whispered and Silent Speech](https://mlsanity.com/paper/1802.06399/) (2018)
- [Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language](https://mlsanity.com/paper/2409.00986/) (2024)
- [OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset](https://mlsanity.com/paper/2301.06375/) (2023)
- [The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?](https://mlsanity.com/paper/2606.07435/) (2026)

## Abstract (arXiv)

We present a personalized Korean visual speech recognition (VSR) system and quantify, on the nine-camera OLKAVS corpus, the gap between the population-level benchmark score and an individual user's error. A video-only Conformer initialized from English-trained weights attains 9.95 - 12.19% character error rate (CER) under the corpus protocol against the published 26.64, and 19.00 - 21.52 on unseen wording. Per speaker, CER spans 1.0 to 52.2%, with seen wording lowering CER by 7.0 - 9.0 points and professional delivery and spontaneous speech raising it by 8.5 - 10.5 and 12.7 points. A low-rank adapter with 4.6% of the parameters, trained on 4 to 29 minutes of the user's frontal video, lowers the CER of twelve high-error speakers by 2.13 to 3.58 points, transfers to every camera without loss, and keeps 85% of the full fine-tuning gain at 12% of its cost to other speakers. Cameras above the mouth plane add about six CER points as a constant offset that training on all views keeps small.