Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch is still an issue for many such parties that want to use this service as-is leading to not so optimal results for their task. We propose a simple technique to perform domain adaptation for ASR error correction via machine translation. The machine translation model is a strong candidate to learn a mapping from out-of-domain ASR errors to in-domain terms in the corresponding reference files. We use two off-the-shelf ASR systems in this work: Google ASR (commercial) and the ASPIRE model (open-source). We observe 7% absolute improvement in word error rate and 4 point absolute improvement in BLEU score in Google ASR output via our proposed method. We also evaluate ASR error correction via a downstream task of Speaker Diarization that captures speaker style, syntax, structure and semantic improvements we obtain via ASR correction.

中文翻译：

---

使用机器翻译的 ASR 纠错和域适应

现成的预训练自动语音识别 (ASR) 系统对于构建基于语音的产品的任何规模的公司来说都是一项越来越可行的服务。虽然这些 ASR 系统是在大量数据上进行训练的，但域不匹配仍然是许多希望使用此服务的相关方的问题，因为它们的任务结果不是那么理想。我们提出了一种简单的技术，通过机器翻译为 ASR 纠错执行域自适应。机器翻译模型是学习从域外 ASR 错误到相应参考文件中域内术语的映射的有力候选者。我们在这项工作中使用了两个现成的 ASR 系统：Google ASR（商业）和 ASPIRE 模型（开源）。我们观察到，通过我们提出的方法，在 Google ASR 输出中，单词错误率绝对提高了 7%，BLEU 得分绝对提高了 4 点。我们还通过说话人分类的下游任务评估 ASR 纠错，该任务捕获我们通过 ASR 校正获得的说话人风格、句法、结构和语义改进。