低资源场景下会话语音的真值和标点联合预测
Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios
摘要：
大写和标点符号是理解书面文本和会话记录的重要线索。然而，许多ASR系统不产生标点和大小写格式的语音转录。我们建议使用一个多任务系统，可以利用套管和标点符号之间的关系，以提高其预测性能。而文本数据预测标点符号和truecasing似乎是丰富的，我们认为，书面文本资源是不够的会话模型的训练数据。我们通过比较标点符号和词的情况下的联合分布，并通过测试我们的模型跨域量化书面和会话文本域之间的不匹配。此外，我们表明，通过在书面文本域中训练模型，然后将迁移学习转移到对话中，我们可以用更少的数据实现合理的性能。
英文摘要：
Capitalization and punctuation are important cues for comprehending written texts and conversational transcripts. Yet, many ASR systems do not produce punctuated and case-formatted speech transcripts. We propose to use a multi-task system that can exploit the relations between casing and punctuation to improve their prediction performance. Whereas text data for predicting punctuation and truecasing is seemingly abundant, we argue that written text resources are inadequate as training data for conversational models. We quantify the mismatch between written and conversational text domains by comparing the joint distributions of punctuation and word cases, and by testing our model cross-domain. Further, we show that by training the model in the written text domain and then transfer learning to conversations, we can achieve reasonable performance with less data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
