Recent years have seen growing interest in conversational agents, such as
chatbots, which are a very good fit for automated customer support because the
domain in which they need to operate is narrow. This intere
采用序列到序列模型解决语音识别误差对于开放域端到端对话生成的影响。将任务看做一个域适应问题,使用两个不同域的 ASR 转录和原始文本,并提出了两个独立编码器的模型,使其隐藏状态相似,并确保解码器预测相同的对话文本。实验结果表明该方法可以消除语音识别错误并帮助口语对话系统生成更相似于原始文本答案的响应。