Multimodal word discovery (MWD) is often treated as a byproduct of the speech-to-image retrieval problem. However, our theoretical analysis shows that some kind of alignment/attention mechanism is crucial for a MWD system to learn meaningful word-level representation. We verify our theory by conducting retrieval and word discovery experiments on MSCOCO and Flickr8k, and empirically demonstrate that both neural MT with self-attention and statistical MT achieve word discovery scores that are superior to those of a state-of-the-art neural retrieval system, outperforming it by 2% and 5% alignment F1 scores respectively.@en

A partial carrier stored and hole path floating dummy shield trench IGBT (PCS-FD-IGBT) is proposed and investigated by simulation. Under E_off of 8mJ/cm², the V_CE(sat)) of 1200V class PCS-FD-IGBT is 1.223V, which is 11.1% and 2.2% less than CON-FD-IGBT and HP-FD-IGBT. Besides, the EMI noise of PCS-FD-IGBT is suppressed at a lower level (dV/dt is below 80kV/μs). Moreover, the PCS-FD-IGBT improves the gate drive controllability to easily adapt the larger range of system inductance.

@en