A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)(2018)
摘要
Lattice-rescoring is a common approach to take advantage of recurrent neural language models in ASR, where a word-lattice is generated from 1st-pass decoding and the lattice is then rescored with a neural model, and an
n
-gram approximation method is usually adopted to limit the search space. In this work, we describe a pruned lattice-rescoring algorithm for ASR, improving the n-gram approximation method. The pruned algorithm further limits the search space and uses heuristic search to pick better histories when expanding the lattice. Experiments show that the proposed algorithm achieves better ASR accuracies while running much faster than the standard algorithm. In particular, it brings a 4x speedup for lattice-rescoring with 4-gram approximation while giving better recognition accuracies than the standard algorithm.
更多查看译文
关键词
automatic speech recognition, recurrent neural network language model, lattice-rescoring, heuristic search
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络