Phonemes are defined by their relationship to words: changing a phoneme changes the word. Learning a phoneme inventory with little supervision has been a longstanding challenge with important applications to under-resourced speech technology. In this paper, we bridge the gap between the linguistic and statistical definition of phonemes and propose a novel neural discrete representation learning model for self-supervised learning of phoneme inventory with raw speech and word labels. Given the availability of phoneme segmentation and some mild conditions, we prove that the phoneme inventory learned by our approach converges to the true one with an exponentially low error rate. Moreover, in experiments on TIMIT and Mboshi benchmarks, our approach consistently learns a better phoneme-level representation and achieves a lower error rate in a zero-resource phoneme recognition task than previous state-of-the-art self-supervised representation learning algorithms.

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.

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.