基于循环神经网络语言模型的N-best重打分算法

N-best Rescoring Algorithm Based on Recurrent Neural Network Language Model

循环神经网络语言模型能够克服统计语言模型中存在的数据稀疏问题,同时具有更强的长距离约束能力,是一种重要的语言模型建模方法。但在语音解码时,由于该模型使词图的扩展次数过多,造成搜索空间过大而难以使用。本文提出了一种基于循环神经网络语言模型的N-best重打分算法,利用N-best引入循环神经网络语言模型概率得分,对识别结果进行重排序,并引入缓存模型对解码过程进行优化,得到最优的识别结果。实验结果表明,本文方法能够有效降低语音识别系统的词错误率。

Recurrent neural network language model （RNNLM ） is an important method in statistical lan‐guage models because it can tackle the data sparseness problem and contain a longer distance constraints . However ,it lacks practicability because the lattice has to expand too many times and explode the search space .Therefore ,a N‐best rescoring algorithm is proposed which uses the RNNLM to rerank the recog‐nition results and optimize the decoding process .Experimental results show that the proposed method can effectively reduce the word error rate of the speech recognition system .