Zhenbiao Chen

Learn More
Support Vector Machines have merged as a pattern classifier and have been shown to be successful in some tasks in the realm of speech processing. This paper explores the issues involved in applying SVMs to asymmetrical situations, namely. beavy sample ratio bias between different classes and different costs for different types of misclassification error. We(More)
In this paper, instead of designing new features based on intuition, linguistic knowledge and domain, we learn some new and effective features using the deep autoencoder (DAE) paradigm for phrase-based translation model. Using the unsupervised pre-trained deep belief net (DBN) to initialize DAE’s parameters and using the input original phrase features as a(More)
This paper presents a new approach that uses linguistic knowledge and pronunciation space for automatic detection of typical phone-level errors made by non-native speakers of mandarin. Firstly, linguistic knowledge of common learner mistakes is embedded in the calculation of log-posterior probability and the revised log-posterior probability (RLPP) is(More)
This paper describes a Japanese-to-Chinese spoken language translation (SLT) method based on simple expression and presents the experimental results. The method is aimed at developing a compact speech translation system, which is robust for spontaneous spoken language phenomena, including the recognition errors and different expression from various(More)
In this paper we propose a phrase-based translation system. In the system, we use phrase translation model instead of word-based model. An improved method to compute phrase translation probability is studied. A phrase-based decoder we developed employs a beam search algorithm, in which some target language words that have both high frequency of appearance(More)
We present a phrase-based method to extract parallel fragments from the comparable corpora. We do this by introducing a force decoder based on the hierarchical phrase-based (HPB) translation model to detect the alignments in comparable sentence pairs. This method enables us to extract useful training data for statistical machine translation (SMT) system. We(More)
In this paper, we describe the CASIA statistical machine translation (SMT) system for the IWSLT2013 Evaluation Campaign. We participated in the Chinese-English and English-Chinese translation tasks. For both of these tasks, we used a hierarchical phrase-based (HPB) decoder and made it as our baseline translation system. A number of techniques were proposed(More)
This paper examines techniques of discriminative optimization for acoustic model, including both HMM parameters and linear transforms, in the context of HUB5 Mandarin large vocabulary speech recognition task, with the aim to partly solve the problems brought by the sparseness and the highly ambiguous nature of the telephony conversational speech data. Three(More)