Filler Prediction Based on Bidirectional LSTM for Generation of Natural Response of Spoken Dialog
Filler Prediction Based on Bidirectional LSTM for Generation of Natural Response of Spoken Dialog
复制标题
DOI：
10.1109/gcce50665.2020.9291867
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Yoshihiro Yamazaki;Yuya Chiba;Takashi Nose;Akinori Ito
中科院分区：
文献类型：
--
作者：
Yoshihiro Yamazaki;Yuya Chiba;Takashi Nose;Akinori Ito
大多数传统的响应生成模型不生成包括填充语的言语不流利，因为它们是从书面语言语料库中训练的。为了训练口语的反应生成模型，有必要在书面句子中插入填充物。本文提出了基于双向LSTM的填充预测模型（BLSTM）。该方法可以考虑整个话语，同时对填充词的位置和种类进行建模。实验表明，该方法在预测精度上优于传统方法。
Most of the conventional response generation models do not generate speech disfluencies including fillers, because they are trained from a written language corpus. It is necessary to insert fillers to written sentences for training a response generation model for the spoken language. In this paper, we proposed the filler prediction model based on bidirectional LSTM (BLSTM). This approach can consider a whole utterance and model both positions and kinds of fillers simultaneously. The experiments showed that the proposed method surpasses the conventional approach in terms of the prediction accuracy.