CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge
This addresses the need for benchmarks in Chinese visual speech recognition, but it is incremental as it builds on existing VSR methods.
The paper tackled the problem of Chinese continuous visual speech recognition by organizing a challenge with single-speaker and multi-speaker tasks, resulting in the best submission significantly outperforming the baseline, especially in the single-speaker task.
The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1) Single-speaker VSR for a particular speaker and (2) Multi-speaker VSR for a set of registered speakers. The challenge yielded highly successful results, with the best submission significantly outperforming the baseline, particularly in the single-speaker task. This paper comprehensively reviews the challenge, encompassing the data profile, task specifications, and baseline system construction. It also summarises the representative techniques employed by the submitted systems, highlighting the most effective approaches. Additional information and resources about this challenge can be accessed through the official website at http://cnceleb.org/competition.