Continuous speech recognition system based on wordnet language model

Abstract

The invention discloses a continuous speech recognition system based on a wordnet language model. The system comprises a speech input module, a feature extraction module, an acoustic model layer search module, a lexical layer search module and a syntax layer search module. The input end of an acoustic model layer is connected with an acoustic model. The input end of the lexical layer search module is connected with a lexical information library. The input end of the syntax layer search module is connected with a syntax information library. According to the invention, a speech recognition process is divided into the acoustic model layer, a lexical layer and a syntax layer; sub words are searched through the acoustic model layer to acquire a candidate sub word sequence; entries are searched according to the lexical information and the language model of words on the lexical layer to acquire a candidate entry sequence; syntax layer searching is carried out according to grammar, semantic information and the language model of other sentences to acquire a final recognition result; and a speech signal is processed step by step in the manner, which is helpful to improve the recognition accuracy and the recognition efficiency of the speech signal.

Description

technical field [0001] The invention belongs to the technical field of speech recognition, in particular to a continuous speech recognition system based on a word net language model. Background technique [0002] With the development of computer science and information technology, speech recognition technology has gradually become the main tool for human-machine interaction. After decades of research and development, speech recognition technology has gradually matured and gradually become practical, and is gradually changing people's way of life. Computers have penetrated into every corner of human life. In modern society, humans are gradually using computers to complete various tasks. In this situation, how to realize the intelligent interaction between human and computer has become an important research topic in the field of artificial intelligence. Speech is the most habitual and natural way of human communication, so speech recognition becomes an ideal choice for huma...

AI Technical Summary

Problems solved by technology

[0003] At present, speech recognition has made some progress, but there is still a big gap from the real free communication between man and machine, which is mainly manifested in: the phenomenon of synergistic pronunciation; the poor adaptability of the speech recognition system; the difficulty of endpoint detection; how to integrate linguistics The effective application of research results in speech recognition, physiology, and psychology still needs to be further studied; there is still little known about human auditory comprehension, knowledge accumulation and learning mechanisms, and the control mechanism of the brain nervous system. How to apply this aspect The existing results are used for speech recognition, which is also a difficult problem

Images