# The GUA-Speech System Description for CNVSRC Challenge 2023

arXiv: https://arxiv.org/abs/2312.07254 · HTML: https://mlsanity.com/paper/2312.07254/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [End-to-end Audio-visual Speech Recognition with Conformers](https://mlsanity.com/paper/2102.06657/) (2021)
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [Visual Speech Recognition for Multiple Languages in the Wild](https://mlsanity.com/paper/2202.13084/) (2022)
- [Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions](https://mlsanity.com/paper/2104.02724/) (2021)
- [WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2203.15455/) (2022)
- [U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition](https://mlsanity.com/paper/2106.05642/) (2021)
- [Audio-Visual Efficient Conformer for Robust Speech Recognition](https://mlsanity.com/paper/2301.01456/) (2023)

## Abstract (arXiv)

This study describes our system for Task 1 Single-speaker Visual Speech Recognition (VSR) fixed track in the Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023. Specifically, we use intermediate connectionist temporal classification (Inter CTC) residual modules to relax the conditional independence assumption of CTC in our model. Then we use a bi-transformer decoder to enable the model to capture both past and future contextual information. In addition, we use Chinese characters as the modeling units to improve the recognition accuracy of our model. Finally, we use a recurrent neural network language model (RNNLM) for shallow fusion in the inference stage. Experiments show that our system achieves a character error rate (CER) of 38.09% on the Eval set which reaches a relative CER reduction of 21.63% over the official baseline, and obtains a second place in the challenge.