Language model re-evaluation method based on long and short memory network

Abstract

The invention provides a language model re-evaluation method based on long and short memory network. The method includes the following steps: a step 100 of inputting to-be-identified language information, and pre-processing the input to-be-identified language information; a step 101 of conducting one-time decoding on the pre-processed information with an N-gram grammar language model, then selecting M optimal candidate results; a step 102 of introducing the identifying result of the one-time decoding to the acquired M optimal candidate results as historical sentence information; a step 103 of re-evaluating the selected M optimal candidate results with the n-gram language model; a step 104 of re-evaluating the M optimal candidate results that are introduced with the historical sentence information by using a neural network training language model which is based on a LSTM structure; and a step 105 of combining the result of the re-evaluation obtained by using the n-gram language model with the result of the re-evaluation obtained by using the neural network language model which is based on the LSTM, selecting an optimal result as the final identification result of the to-be-identified language information.

Description

technical field [0001] The invention relates to the field of speech recognition, and is a method for reassessing recognition results by using a long-short-term memory network language model, thereby improving speech recognition performance. Background technique [0002] The language model describes the constraint phenomenon between words in linguistics in a mathematical way, and plays a significant role in the field of speech recognition, especially in the speech recognition system for telephone conversations, the colloquial language model can often be greatly improved Significantly improve system performance. However, language models are domain- and time-sensitive, real-life phone conversation-style corpora are limited, and real speech quality is varied and all-encompassing, so speech recognition rates are usually low. In order to improve the performance of the speech recognition system, a post-processing stage is generally added, that is, the first-pass decoding not only ...

AI Technical Summary

Problems solved by technology

[0004] In the speech recognition system, the effect of using the high-element language model for re-evaluation is not obvious, and the performance improvement is limited by using the forward neural network language model and the recursive neural network language model for M candidate re-evaluation.

Because none of these language models can perform a good memory function on historical information

Images