TY - GEN
T1 - Response Obligation Estimation That Considers Users' Repetitive Utterances using Knowledge-Guided Random Forest
AU - Funakoshi, Kotaro
AU - Yamagami, Ryota
AU - Sugano, Shigeki
AU - Nakano, Mikio
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Response obligation is whether a spoken dialogue system should react to an input sound. This paper focuses on the false negative errors in response obligation estimation (ROE) that are displayed as the system's neglect of its users. When the users repeat after the system ignores their speech, ROE will likely fail again because the repeated input is similar to the previous input. Therefore, we propose an improved ROE method that considers users' repetitions. First, we show that a simple concatenation of ROE and repetition features is better than two other integration architectures. Then, we propose a modified random forest algorithm that incorporates human domain knowledge. The effectiveness is demonstrated with simulated repetitions as a 7.6-point gain from the baseline.
AB - Response obligation is whether a spoken dialogue system should react to an input sound. This paper focuses on the false negative errors in response obligation estimation (ROE) that are displayed as the system's neglect of its users. When the users repeat after the system ignores their speech, ROE will likely fail again because the repeated input is similar to the previous input. Therefore, we propose an improved ROE method that considers users' repetitions. First, we show that a simple concatenation of ROE and repetition features is better than two other integration architectures. Then, we propose a modified random forest algorithm that incorporates human domain knowledge. The effectiveness is demonstrated with simulated repetitions as a 7.6-point gain from the baseline.
KW - human-robot interaction
KW - knowledge-guided machine learning
KW - multimodal dialogue
UR - http://www.scopus.com/inward/record.url?scp=85082650435&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082650435&partnerID=8YFLogxK
U2 - 10.1109/Humanoids43949.2019.9035079
DO - 10.1109/Humanoids43949.2019.9035079
M3 - Conference contribution
AN - SCOPUS:85082650435
T3 - IEEE-RAS International Conference on Humanoid Robots
SP - 99
EP - 105
BT - 2019 IEEE-RAS 19th International Conference on Humanoid Robots, Humanoids 2019
PB - IEEE Computer Society
T2 - 19th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019
Y2 - 15 October 2019 through 17 October 2019
ER -