The paper studies a new method for Chinese new word detection and emotional tendency judgment based on mixed model and proposes a new word generation *** we construct conditional random fields(CRFs) to recognize the n...
详细信息
ISBN:
(纸本)9781467369541
The paper studies a new method for Chinese new word detection and emotional tendency judgment based on mixed model and proposes a new word generation *** we construct conditional random fields(CRFs) to recognize the new words,lead-in features based on character combined with the crowd sourcing network *** then express word as a word vector based on neural network language model(NNLM) to judge the new word emotional *** experimental results show that the method can improve the precision and recall of the new word detection with a good system performance,and it also provides a new way for forecasting the public mood.
This paper presents continuation of research on Structured OUt-put Layer neural network language models (SOUL NNLM) for automatic speech recognition. As SOUL NNLMs allow estimating probabilities for all in-vocabulary ...
详细信息
ISBN:
(纸本)9781618392701
This paper presents continuation of research on Structured OUt-put Layer neural network language models (SOUL NNLM) for automatic speech recognition. As SOUL NNLMs allow estimating probabilities for all in-vocabulary words and not only for those pertaining to a limited shortlist, we investigate. its performance on a large-vocabulary task. Significant improvements both in perplexity and word error rate over conventional shortlist-based NNLMs are shown on a challenging Arabic GALE task characterized by a recognition vocabulary of about 300k entries. A new training scheme is proposed for SOUL NNLMs that is based on separate training of the out-of-shortlist part of the output layer. It enables using more data at each iteration of a neuralnetwork without any considerable slow-down in training and brings additional improvements in speech recognition performance.
In this paper, we study the use of morphological and syntactic context features to improve speech recognition of a morphologically rich language like Arabic. We examine a variety of syntactic features, including part-...
详细信息
ISBN:
(纸本)9781424442966
In this paper, we study the use of morphological and syntactic context features to improve speech recognition of a morphologically rich language like Arabic. We examine a variety of syntactic features, including part-of-speech tags, shallow parse tags, and exposed head words and their non-terminal labels both before and after the word to be predicted. neuralnetwork LMs are used to model these features since they generalize better to unseen events by modeling words and other context features in continuous space. Using morphological and syntactic features, we can improve the word error rate (WER) significantly on various test sets, including EVAL'08U, the unsequestered portion of the DARPA GALE Phase 3 evaluation test set.
neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisation and discriminative power. This pa...
详细信息
ISBN:
(纸本)9781617821233
neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisation and discriminative power. This paper present two techniques to improve performance of standard NNLMs. First, the form of NNLM is modelled by introduction an additional output layer node to model the probability mass of out-of-shortlist (OOS) words. An associated probability normalisation scheme is explicitly derived. Second, a novel NNLM adaptation method using a cascaded network is proposed. Consistent WER reductions were obtained on a state-of-the-art Arabic LVCSR task over conventional NNLMs. Further performance gains were also observed after NNLM adaptation.
In this paper, we study the use of morphological and syntactic context features to improve speech recognition of a morphologically rich language like Arabic. We examine a variety of syntactic features, including part-...
详细信息
ISBN:
(纸本)9781424442959
In this paper, we study the use of morphological and syntactic context features to improve speech recognition of a morphologically rich language like Arabic. We examine a variety of syntactic features, including part-of-speech tags, shallow parse tags, and exposed head words and their non-terminal labels both before and after the word to be predicted. neuralnetwork LMs are used to model these features since they generalize better to unseen events by modeling words and other context features in continuous space. Using morphological and syntactic features, we can improve the word error rate (WER) significantly on various test sets, including EVAL'08U, the unsequestered portion of the DARPA GALE Phase 3 evaluation test set.
暂无评论