A new decoder based on a generalized confidence score
نویسندگان
چکیده
We propose a new decoder based on a generalized confidencescore. The generalized confidence score is defined as a product of confidence scores obtained from confidence information sources such as likelihood, likelihood ratio, duration, duration ratio, language model probabilities, supra-segmental information etc. All confidence information sources are converted into confidence scores by a confidence pre-processor. We show an extended hybrid decoder as an example of the decoder based on the generalized confidence score. The extended hybrid decoder uses multi-level confidence scores such as frame-level, phone-level, and word-level likelihood ratios, while the conventional hybrid decoder uses the frame-level confidence score. Experimental result shows that the extended decoder gives better result than the conventional hybrid decoder, particularly in dealing with out-of-vocabulary words or out-of-task sentences.
منابع مشابه
A Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کاملFUZZY RISK ANALYSIS BASED ON A NEW METHOD FOR RANKING GENERALIZED FUZZY NUMBERS
Fuzzy risk analysis, as a powerful tool to address uncertain information, can provide an appropriate method for risk analysis. However, the previous fuzzy risk analysis methods still have some weaknesses. To overcome the weaknesses of existing fuzzy risk analysis methods, a novel method for ranking generalized fuzzy numbers is proposed for addressing fuzzy risk analysis problems. In the propose...
متن کاملA New Phrase-based System Combination Framework for MT
This paper presents a new phrase-based combination framework for combining outputs of different machine translation (MT) systems. We build a sentencespecific translation option table by collecting source-to-target phrases over the input translations and assigning a confidence score to each phrase by exploiting their similarity to all the other phrases. Using this translation option table inside...
متن کاملA New Low-Costing QC-LDPC Decoder for FPGA
Based on the Generalized Distributive Law and the features of FPGAs, this paper proposes a new strategy for implementation of Low-Costing QC-LDPC Decoder on FPGA platform. We get this new strategy from the Generalized Distributive Law, which is proposed to describe the belief propagation on graphs. And using this new strategy a low-costing (2560, 1024) LDPC decoder is implemented on a Xilinx Vi...
متن کاملA generalized ABFT technique using a fault tolerant neural network
In this paper we first show that standard BP algorithm cannot yeild to a uniform information distribution over the neural network architecture. A measure of sensitivity is defined to evaluate fault tolerance of neural network and then we show that the sensitivity of a link is closely related to the amount of information passes through it. Based on this assumption, we prove that the distribu...
متن کامل