Research in surgical robotics has an established track record at Imperial College, and a number of research and commercial surgical robot platforms have been developed over the years. The Hamlyn Centre is a champion for technological innovation and clinical adoption of robotic, minimally invasive surgery. We work in partnership with major industrial leaders in medical devices and surgical robots, as well as developing our own platforms such as the i-Snake® and Micro-IGES platforms. The Da Vinci surgical robot is used extensively for endoscopic radical prostatectomy, hiatal hernia surgery, and low pelvic and rectal surgery, and in 2003, St Mary’s Hospital carried out its first Totally Endoscopic Robotic Coronary Artery Bypass (TECAB).

The major focus of the Hamlyn Centre is to develop robotic technologies that will transform conventional minimally invasive surgery, explore new ways of empowering robots with human intelligence, and develop[ing miniature 'microbots' with integrated sensing and imaging for targeted therapy and treatment. We work closely with both industrial and academic partners in open platforms such as the DVRK, RAVEN and KUKA. The Centre also has the important mission of driving down costs associated with robotic surgery in order to make the technology more accessible, portable, and affordable. This will allow it to be fully integrated with normal surgical workflows so as to benefit a much wider patient population.

The Hamlyn Centre currently chairs the UK Robotics and Autonomous Systems (UK-RAS) Network. The mission of the Network is to to provide academic leadership in Robotics and Autonomous Systems (RAS), expand collaboration with industry and integrate and coordinate activities across the UK Engineering and Physical Sciences Research Council (EPSRC) funded RAS capital facilities and Centres for Doctoral Training (CDTs).


Citation

BibTex format

@article{Liu:2014:10.1016/j.specom.2014.11.004,
author = {Liu, J and Yang, GZ},
doi = {10.1016/j.specom.2014.11.004},
journal = {Speech Communication},
pages = {65--77},
title = {Robust speech recognition in reverberant environments by using an optimal synthetic room impulse response model},
url = {http://dx.doi.org/10.1016/j.specom.2014.11.004},
volume = {67},
year = {2014}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - This paper presents a practical technique for Automatic speech recognition (ASR) in multiple reverberant environment selection. Multiple ASR models are trained with artificial synthetic room impulse responses (IRs), i.e. simulated room IRs, with different reverberation time (T60Models) and tested on real room IRs with varying T60Rooms. To apply our method, the biggest challenge is to choose a proper artificial room IR model for training ASR models. In this paper, a generalised statistical IR model with attenuated reverberation after an early reflection period, named attenuated IR model, has been adopted based on three time-domain statistical IR models. Its optimal values of the reverberation-attenuation factor and the early reflection period on the recognition rate have been searched and determined. Extensive testing has been performed over four real room IR sets (63 IRs in total) with variant T60Rooms and speaker microphone distances (SMDs). The optimised attenuated IR model had the best performance in terms of recognition rate over others. Specific considerations of the practical use of the method have been taken into account including: (i) the maximal training step of T60Model in order to get the minimal number of models with acceptable performance; (ii) the impact of selection errors on the ASR caused by the estimation error of T60Room; and (iii) the performance over SMD and direct-to-reverberation energy Ratio (DRR). It is shown that recognition rates of over 80∼∼90% are achieved in most cases. One important advantage of the method is that T60Room can be estimated either from reverberant sound directly ( Takeda et al., 2009, Falk and Chan, 2010 and Löllmann et al., 2010) or from an IR measured from any point of the room as it remains constant in the same room ( Kuttruff, 2000), thus it is particularly suited to mobile applications. Compared to many classical dereverberation methods, the proposed method is more suited to ASR tasks in multiple reverb
AU - Liu,J
AU - Yang,GZ
DO - 10.1016/j.specom.2014.11.004
EP - 77
PY - 2014///
SN - 1872-7182
SP - 65
TI - Robust speech recognition in reverberant environments by using an optimal synthetic room impulse response model
T2 - Speech Communication
UR - http://dx.doi.org/10.1016/j.specom.2014.11.004
UR - http://hdl.handle.net/10044/1/27009
VL - 67
ER -