N-best error simulation for training spoken dialogue systems

A recent trend in spoken dialogue research is the use of reinforcement learning to train dialogue systems in a simulated environment. Past researchers have shown that the types of errors that are simulated can have a significant effect on simulated dialogue performance. Since modern systems typically receive an N-best list of possible user utterances, it is important to be able to simulate a full N-best list of hypotheses. This paper presents a new method for simulating such errors based on logistic regression, as well as a new method for simulating the structure of N-best lists of semantics and their probabilities, based on the Dirichlet distribution. Off-line evaluations show that the new Dirichlet model results in a much closer match to the receiver operating characteristics (ROC) of the live data. Experiments also show that the logistic model gives confusions that are closer to the type of confusions observed in live situations. The hope is that these new error models will be able to improve the resulting performance of trained dialogue systems. © 2012 IEEE.

Complementary Phone Error training

This paper introduces a novel method for the training of a complementary acoustic model with respect to set of given acoustic models. The method is based upon an extension of the Minimum Phone Error (MPE) criterion and aims at producing a model that makes complementary phone errors to those already trained. The technique is therefore called Complementary Phone Error (CPE) training. The method is evaluated using an Arabic large vocabulary continuous speech recognition task. Reductions in word error rate (WER) after combination with a CPE-trained system were obtained with up to 0.7% absolute for a system trained on 172 hours of acoustic data and up to 0.2% absolute for the final system trained on nearly 2000 hours of Arabic data.

Training and assignment of multi-skilled workers for implementing seru production systems

Confronted with high variety and low volume market demands, many companies, especially the Japanese electronics manufacturing companies, have reconfigured their conveyor assembly lines and adopted seru production systems. Seru production system is a new type of work-cell-based manufacturing system. A lot of successful practices and experience show that seru production system can gain considerable flexibility of job shop and high efficiency of conveyor assembly line. In implementing seru production, the multi-skilled worker is the most important precondition, and some issues about multi-skilled workers are central and foremost. In this paper, we investigate the training and assignment problem of workers when a conveyor assembly line is entirely reconfigured into several serus. We formulate a mathematical model with double objectives which aim to minimize the total training cost and to balance the total processing times among multi-skilled workers in each seru. To obtain the satisfied task-to-worker training plan and worker-to-seru assignment plan, a three-stage heuristic algorithm with nine steps is developed to solve this mathematical model. Then, several computational cases are taken and computed by MATLAB programming. The computation and analysis results validate the performances of the proposed mathematical model and heuristic algorithm. © 2013 Springer-Verlag London.

Adult rat retinal ganglion cells and glia can be printed by piezoelectric inkjet printing.

We have investigated whether inkjet printing technology can be extended to print cells of the adult rat central nervous system (CNS), retinal ganglion cells (RGC) and glia, and the effects on survival and growth of these cells in culture, which is an important step in the development of tissue grafts for regenerative medicine, and may aid in the cure of blindness. We observed that RGC and glia can be successfully printed using a piezoelectric printer. Whilst inkjet printing reduced the cell population due to sedimentation within the printing system, imaging of the printhead nozzle, which is the area where the cells experience the greatest shear stress and rate, confirmed that there was no evidence of destruction or even significant distortion of the cells during jet ejection and drop formation. Importantly, the viability of the cells was not affected by the printing process. When we cultured the same number of printed and non-printed RGC/glial cells, there was no significant difference in cell survival and RGC neurite outgrowth. In addition, use of a glial substrate significantly increased RGC neurite outgrowth, and this effect was retained when the cells had been printed. In conclusion, printing of RGC and glia using a piezoelectric printhead does not adversely affect viability and survival/growth of the cells in culture. Importantly, printed glial cells retain their growth-promoting properties when used as a substrate, opening new avenues for printed CNS grafts in regenerative medicine.