In this paper we present preliminary evaluations on the large vocabulary speech decoder we are currently developing at Tokyo Institute of Technology. Our goal is to build a scalable and flexible decoder to operate on weighted finite state transducer (WFST) search spaces. Even though the development of the decoder is still in its infancy we are already achieving good accuracy and speed on a larg...

A new neural prosthetic decoder architecture is presented which uses a hidden Markov model of typical arm movements to assist the reconstruction of intended trajectories from an ensemble of neural signals. The use of such a model results in a decoder which is robust to fewer or smaller neural signals. With limited information, the average error of the reconstructed trajectories produced by the ...

This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows significant improvement over a strong RNN-based encoder-decoder baseline and ac...

Cohesive constraints allow the phrase-based decoder to employ arbitrary, non-syntactic phrases, and encourage it to translate those phrases in an order that respects the source dependency tree structure. We present extensions of the cohesive constraints, such as exhaustive interruption count and rich interruption check. We show that the cohesion-enhanced decoder significantly outperforms the st...

In contrast to a maximum-likelihood decoder, it is often desirable to use an incomplete decoder that can detect its decoding errors with high probability. One common choice is the bounded distance decoder. Bounds are derived for the total word error rate, Pw, and the undetected error rate, Pu. Excellent agreement is found with simulation results for a small code, and the bounds are shown to be ...

This paper introduces a new class of Huffman decoders which is a developmet of the parallel Huffman decoder model. With pipelining and partitioning, a regular architecture with an arbitrary degree of pipelining is developed. The proposed architecture dramatically reduces the symbol decoder requirements compared to previous results, and still is the actual implementation of the symbol decoder no...

A kind of (1008, 3, 6) rules LDPC decoder was designed in this paper, in order to solving the high complexity of LDPC decoder hardware implementation, which adopted Min-Sum decoding algorithm and partparallel structure. The minimum module in the traditional check function unit (CFU) was improved, which could reduce the complexity of the hardware realization. In the end, the LDPC decoder achieve...

The design and implementation of a flexible LDPC decoder able to cope with different codes, is gathering an increasing interest in the scientific community. Roughly speaking, a flexible decoder exhibits the remarkable ability of being able to decode different codes resorting to the same hardware. In this paper we present a novel decoder architecture specifically devised to present an high flexi...