|
Circumventing the Fundamental Tradeoff Between Stability and Performance in Haptic Rendering - Successive Force Augment Approach |
|
Harsimran Singh, Jee-Hwan Ryu(Korea University of Technology and Education, Korea) |
| This paper proposes a new approach to further enlarge the achievable displayed stiffness range of impedance-type haptic interfaces. Most of the stability guaranteed haptic interaction methods result having much lower achieved stiffness than the original desired stiffness at the cost of stability. This paper introduces a new rendering approach, which can display close to the originally intended high stiffness by only using low value of stiffness in the rendering of the state dependent linear force feedback force together with the state independent feedforward force offset. |
|
|
Mobile Robot Navigation for Human-Robot Social Interaction |
|
Pakpoom Patompak, Sungmoon Jeong, Nak Young Chong(Japan Advanced Institute of Science And Technology, Japan), Itthisek Nilkhamhang(Sirindhorn International Institute of Technology, Thailand) |
| Human social interactions are believed to be described by a mathematical model called the Social Force Model (SFM)which has often used the SFM to generate an appropriate navigation behavior in mobile robot navigation researches. However, to create a mobile robot that moves around in a human-populated environment in a socially acceptable way, it should be stressed that the social conventions are strictly obeyed. This paper proposes an extended SFM between humans and robots, called the Social Relationship Model (SRM), to enable mobile robots to generate navigation paths in a human-like manner. |
|
|
Detecting Pilot's Utterance: An Adaptive Keyword Spotting Approach |
|
Xinyang Zhu(Shanghai Jiao Tong University, China) |
| The studies of human factors in a flight cockpit require the pilot’s action to be identified and measured precisely. It is a very time-consuming task for analysts to use the traditional manual operating approaches. In this paper, a pilot’s speech analysis method based on Dynamic Time Warping (DTW) technology is proposed as a part of the automatic pilot’s action identification procedure. The keywords spotting is the basis of studying the information of the pilot’s speech. |
|
|
N-best List Re-ranking Using Syntactic Score: An Approach for Improving Speech Recognition Accuracy in Air Traffic Control |
|
Van Nhan Nguyen, Harald Holone(Østfold University College, Norway) |
| Recently, a lot of research has been conducted to bring Automatic Speech Recognition (ASR) into various areas of Air Traffic Control (ATC), such as ATC simulation and training, and ATC workload measurement. However, due to the high accuracy requirements of the ATC context and its unique challenges, ASR has not been widely adopted in this field. In this paper, we aim at improving the accuracy of ASR systems in ATC by performing n-best list re-ranking using syntactic knowledge. The results shows that our proposed approach reduces 1.21% and 0.21% WER on the ATCSC and ATCOSIM corpora respectively. |
|
|
N-best List Re-ranking Using Semantic Relatedness and Syntactic Score: An Approach for Improving Speech Recognition Accuracy in Air Traffic Control |
|
Van Nhan Nguyen, Harald Holone(Østfold University College, Norway) |
| In this paper, we investigate how we can take advantage of the availability of linguistic knowledge, particularly
semantic knowledge, in Air Traffic Control (ATC) to improve the accuracy of Automatic Speech Recognition
(ASR) systems. To facilitate this, we integrate semantic knowledge into post-processing by performing n-best list
re-ranking. The evaluation results show that our proposed approach reduces the WER by 0.31% and 1.53% on the ATCOSIM and ATCSC corpora respectively. Our proposed approach also shows 19.93% WER improvement compared with traditional n-gram model on the ATCSC corpus. |
| |