Gökhan Ince, Kazuhiro Nakadai, Tobias Rodemann, Jun-ichi Imura, Keisuke Nakamura, Hirofumi Nakajima, "Incremental Learning for Ego Noise Estimation of a Robot", International Conference on Intelligent Robot and Systems (IROS 2011), 2011.

Using pre-recorded templates to estimate and suppress the ego noise of a robot is advantageous because this method is able to cope with the non-stationarity of this particular type of noise. However, standard template-based estimation requires human intervention in the ofine training sessions, storage of large amounts of data and does not adapt to the dynamical changes in the environmental conditions. In this paper we investigate the feasibility of an incremental template learning system to tackle these drawbacks. Incremental learning enables the system to acquire new templates on the y and update the older ones appropriately. Whilst allowing the system to continually increase its knowledge and enhancing its estimation performance, this learning scheme also reduces the size of the database. We evaluate the performance of the proposed noise estimation method in terms of its estimation accuracy, quality of speech signals enhanced by spectral subtraction method, and size of database. The experimental results show that our system compared to conventional single- channel noise estimation methods achieves better performance in attaining signal quality and improving word correct rates.