Wu Hua

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)
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)
This paper describes a generalized translation memory system, which takes advantage of sentence level matching, sub-sentential matching, and pattern-based machine translation technologies. All of the three techniques generate translation suggestions with the assistance of word alignment information. For the sentence level matching, the system generates the(More)
In this paper, we made comprehensive comparisons of three localization algorithms in wireless sensor network (WSN): A localization algorithm based on virtual central node (VCN), an improved 3D node localization algorithm based on virtual central node (IVCN) and an iterative calculation of secondary grid division (ICSGD) localization scheme. VCN and IVCN(More)
To get good understanding of prosody in continuous speech of Standard Chinese, we have collected large amount of speech in paragraph. 18 read discourse each contains 300-500 syllables are used as reading texts, which cover main discourse We are going effort on linguistic annotation. In This paper we report works reported as follows: One male speaker's(More)
  • 1