Audio-visual speech recognition has received a lot of attention due to its robustness against acoustic noise. Recently, the performance of automatic, visual, and audio-visual speech recognition (ASR, VSR, and AV-ASR, respectively) has been substantially improved, mainly due to the use of larger models and training sets. However, accurate labelling of datasets is time-consuming and expensive. Hence, in this work, we investigate the use of automatically-generated transcriptions of unlabelled datasets to increase the training set size. For this purpose, we use publicly-available pre-trained ASR models to automatically transcribe unlabelled datasets such as AVSpeech and VoxCeleb2. Then, we train ASR, VSR and AV-ASR models on the augmented training set, which consists of the LRS2 and LRS3 datasets as well as the additional automatically-transcribed data. We demonstrate that increasing the size of the training set, a recent trend in the literature, leads to reduced WER despite using noisy transcriptions. The proposed model achieves new state-of-the-art performance on AV-ASR on LRS2 and LRS3. In particular, it achieves a WER of 0.9% on LRS3, a relative improvement of 30% over the current state-of-the-art approach, and outperforms methods that have been trained on non-publicly available datasets with 26 times more training data.

翻译：摘要：音频-视觉语音识别因其对声学噪声的鲁棒性而备受关注。近年来，自动语音识别、视觉语音识别及音频-视觉语音识别（分别简称为ASR、VSR和AV-ASR）的性能显著提升，主要得益于更大规模模型与训练集的使用。然而，数据集的高精度标注既耗时又昂贵。因此，本研究探索利用无标注数据集的自动生成转录文本来扩大训练集规模。为此，我们采用公开可用的预训练ASR模型，对AVSpeech和VoxCeleb2等无标注数据集进行自动转录。随后，在增强训练集（包含LRS2、LRS3数据集及额外自动转录数据）上训练ASR、VSR和AV-ASR模型。实验证明，尽管使用噪声转录，但遵循文献中的近期趋势来扩大训练集规模仍能降低词错误率（WER）。所提模型在LRS2和LRS3数据集上的AV-ASR任务中达到了新的最优性能。特别地，在LRS3数据集上实现了0.9%的词错误率，相比当前最优方法相对提升30%，且优于那些使用非公开数据集训练（训练数据量达26倍）的方法。