Improving speech transcription for Mandarin-english translation

This paper describes the development of the CU-HTK Mandarin Speech-To-Text (STT) system and assesses its performance as part of a transcription-translation pipeline which converts broadcast Mandarin audio into English text. Recent improvements to the STT system are described and these give Character Error Rate (CER) gains of 14.3% absolute for a Broadcast Conversation (BC) task and 5.1% absolute for a Broadcast News (BN) task. The output of these STT systems is then post-processed, so that it consists of sentence-like segments, and translated into English text using a Statistical Machine Translation (SMT) system. The performance of the transcription-translation pipeline is evaluated using the Translation Edit Rate (TER) and BLEU metrics. It is shown that improving both the STT system and the post-STT segmentations can lower the TER scores by up to 5.3% absolute and increase the BLEU scores by up to 2.7% absolute. © 2007 IEEE.

Kick synchronization versus diffusive synchronization

The paper provides an introductory discussion about two fundamental models of oscillator synchronization: the (continuous-time) diffusive model, that dominates the mathematical literature on synchronization, and the (hybrid) kick model, that accounts for most popular examples of synchronization, but for which only few theoretical results exist. The paper stresses fundamental differences between the two models, such as the different contraction measures underlying the analysis, as well as important analogies that can be drawn in the limit of weak coupling. © 2012 IEEE.