This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNN-T) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech ...
详细信息
We give an overview of the RWTH phrase-based statistical machine translation system that was used in the evaluation campaign of the International Workshop on Spoken language Translation 2005. We use a two pass approac...
详细信息
This paper describes an efficient method to extract large n-best lists from a word graph produced by a statistical machine translation system. The extraction is based on the k shortest paths algorithm which is efficie...
详细信息
In this paper, we describe a source-side reordering method based on syntactic chunks for phrase-based statistical machine translation. First, we shallow parse the source language sentences. Then, reordering rules are ...
详细信息
Manual analysis and decryption of enciphered documents is a tedious and error prone work. Often-even after spending large amounts of time on a particular cipher-no decipherment can be found. Automating the decryption ...
详细信息
In this paper, we propose a novel semantic cohesion model. Our model utilizes the predicateargument structures as soft constraints and plays the role as a reordering model in the phrasebased statistical machine transl...
详细信息
We present a method to classify images into different categories of pornographic content to create a system for filtering pornographic images from network traffic. Although different systems for this application were ...
详细信息
The parametric Bayesian Feature Enhancement (BFE) and a datadriven Denoising Autoencoder (DA) both bring performance gains in severe single-channel speech recognition conditions. The first can be adjusted to different...
详细信息
Context-dependent deep neural network HMMs have been shown to achieve recognition accuracy superior to Gaussian mixture models in a number of recent works. Typically, neural networks are optimized with stochastic grad...
详细信息
In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes' theorem. One component is a traditional ungrounded response generatio...
详细信息
暂无评论