Learn More
This paper proposes an approach to improve statistical word alignment with the boosting method. Applying boosting to word alignment must solve two problems. The first is how to build the reference set for the training data. We propose an approach to automatically build a pseudo reference set, which can avoid manual annotation of the training set. The second(More)
Speech corpus of Chinese discourse (ASCCD) was setup and annotated on segmental and prosodic and syntactic tiers. SAMPA-C and C-ToBI conventions are used for segmental and prosodic labeling. Sound variation such as assimilation, insertion and deletion are investigated on the labeled database. The prosodic research focuses on the sentence stress that(More)
Read and spontaneous discourses are two different but very significant speech styles to be investigated. So phonetic labeling on read and spontaneous discourse corpora are made one is ASCCD, a 10 hours read discourse corpus and the other is CASS, a 4 hours spontaneous discourse corpus. First the principles and conventions of transcription are presented.(More)
Mandarin Chinese, a Sino-Tibetan language, has distinct syntactic and morphological structures in comparison to Indo-European languages. This study concerns Chinese infants' initial derivation of grammatical categories. We examined the prosodic properties of nouns and verbs of the maternal input speech. Non-word disyllabic noun-verb homophones were created(More)
TCP has the congestion control algorithm, the behavior of TCP flows can reflect the network status. It is possible to know the network status through the flow statistics such as Net Flow. But different TCP congestion control algorithms take different methods to the same network state. The fully understanding of congestion control mechanism is the(More)
A range-free three dimensional localization scheme based on optimum space step distance (OSSDL) and an improved node self-localization algorithm based on virtual central node (IVCN) for wireless sensor network (WSN) are proposed in our previous papers. By analyzing classic two dimensional DV-Hop localization algorithm, OSSDL algorithm realizes localization.(More)
We propose a 3D localization algorithm used in ship area networks (SANs) in the literature before. In this paper in order to explore more performances of ELCV we made some other comprehensive simulations. In ELCV a classic noise model is introduced to characterize the acoustic background noise observed in SANs. Meanwhile random communication range nodes are(More)
This paper proposes a novel Example-Based Machine Translation (EBMT) method based on Tree String Correspondence (TSC) and statistical generation. In this method, the translation examples are represented as TSC, which consists of three parts: a parse tree in the source language, a string in the target language, and the correspondences between the leaf nodes(More)