A hybrid barge-in procedure for more reliable turn-taking in human-machine dialog systems
A hybrid barge-in procedure for more reliable turn-taking in human-machine dialog systems
复制标题
一种混合打断程序，可在人机对话系统中实现更可靠的轮流
DOI：
10.1109/asru.2003.1318428
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
H. Kim
中科院分区：
文献类型：
--
作者：
R. Rose;H. Kim
本文研究了旨在允许人机对话系统的用户中断或驳回机器生成的语音消息的技术。对从基于电话的对话系统收集的话语进行了一项实验研究，以分析驳船绩效对用户语音的影响。这项研究的结果是，过度的驳船潜伏期导致一半以上用户的话语出现。提出了一种用于从同一域收集的话语进行驳船检测的混合程序。该过程将基于特征的语音活动检测（VAD）算法与基于模型的方法相结合，用于验证假设的语音段。本文中显示了该程序以获得更好的检测性能，而不是依靠语音识别解码器来检测语音的过程。还发现它具有与低延迟基于特征的语音检测算法获得的潜伏期。
This paper investigates techniques designed to allow the users of human-machine dialog systems to interrupt or barge-in over machine generated speech messages. An experimental study was performed on utterances collected from a telephone based dialog system to analyze the effect of barge-in performance on users' speech. One result of this study was that excessive barge-in latencies resulted in disfluencies appearing in over half of users' utterances. A hybrid procedure for barge-in detection is proposed and evaluated on the utterances collected from the same domain. The procedure combines a feature-based voice activity detection (VAD) algorithm with a model-based approach for verifying hypothesized speech segments. The procedure is shown in the paper to obtain better detection performance than procedures that rely on the speech recognition decoder to detect speech. It is also found to have latencies that are comparable to those obtained by low delay feature-based speech detection algorithms.