The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption, aiming to recover transcription errors caused by domain mismatch. Unlike existing correction methods that rely on transcribed audios for training, our approach requires only unlabeled data of the target domains in which a pseudo-labeling technique is applied to generate correction training samples. To reduce over-fitting to the pseudo data, we also propose an encoder-decoder correction model that can take into account additional information such as dialogue context and acoustic features. Experiment results show that our method obtains a significant word error rate (WER) reduction over non-adapted ASR systems. The correction model can also be applied on top of other adaptation approaches to bring an additional improvement of 10% relatively.

本文提出了一种无监督自适应错误校正方法，可以在未见过的领域中恢复由领域差异引起的语音识别错误，使用伪标记技术生成学习样本，在持续学习中以减少过度拟合，并使用编码器-解码器校正模型结合其他信息以进一步提高适应性，实验结果表明，该方法相对于未自适应的ASR系统显著降低了单词错误率，并可用于其他适应方法以带来额外的10%的性能提升。

无监督领域自适应语音识别与无监督错误校正