In this work, multiple hierarchical language modeling strategies for a zero OOV rate large vocabulary continuous speech recognition system are investigated. In our previously proposed hierarchical approach, a full-wor...
详细信息
In this paper, we dissect the influence of several target-side dependency-based extensions to hierarchical machine translation, including a dependency language model (LM). We pursue a non-restrictive approach that doe...
详细信息
In this paper we present an investigation of sequence-discriminative training of deep neural networks for automatic speech recognition. We evaluate different sequence-discriminative training criteria (MMI and MPE) and...
详细信息
We investigate sequence-discriminative training of long shortterm memory recurrent neural networks using the maximum mutual information criterion. We show that although recurrent neural networks already make use of th...
详细信息
German is a morphologically rich language having a high degree of word inflections, derivations and compounding. This leads to high out-of-vocabulary (OOV) rates and poor language model (LM) probabilities in the large...
详细信息
Performing large vocabulary continuous speech recognition (LVCSR) for morphologically rich languages is considered a challenging task. The morphological richness of such languages leads to high out-of-vocabulary (OOV)...
详细信息
We present a novel toolkit that implements the long short-term memory (LSTM) neural network concept for language modeling. The main goal is to provide a software which is easy to use, and which allows fast training of...
详细信息
In the hybrid approach, neural network output directly serves as hidden Markov model (HMM) state posterior probability estimates. In contrast to this, in the tandem approach neural network output is used as input feat...
详细信息
Inspired by previous chunk-level reordering approaches to statistical machine translation, this paper presents two methods to improve the reordering at the chunk level. By introducing a new lattice weighting factor an...
详细信息
During the last few years, the statistical approach has found widespread use in machine translation, in particular for spoken language. In many comparative evaluations of automatic speech translation, the statistical ...
详细信息
During the last few years, the statistical approach has found widespread use in machine translation, in particular for spoken language. In many comparative evaluations of automatic speech translation, the statistical approach was found to be significantly superior to the existing conventional approaches. The paper will present the main components of a statistical machine translation system (such as alignment and lexicon models, training procedure, generation of the target sentence) and summarize the progress made so far. We will conclude with a roadmap for future research on spoken language translation.
暂无评论