Voice recognition method based on transfer learning in field of civil aviation air-ground calls

Abstract

The invention discloses a voice recognition method based on transfer learning in the field of civil aviation air-ground calls. The method comprises the steps of collecting a general data set and a transfer data set and performing data processing, initializing a neural network, and adopting a time delay neural network-hidden Markov model as an acoustic training model, performing voice recognition training by using the general data set to obtain a Chinese voice recognition general acoustic model, training the transfer data set on a general Chinese voice recognition model and adjusting parametersto obtain a Chinese voice recognition acoustic model in the civil aviation air-ground call field, and expanding text corpora in the civil aviation field, and generating a language model. According tothe method based on transfer learning, data outside the field can be effectively utilized, and compared with a common acoustic model, the recognition effect is greatly improved. By adopting the method, the problem of insufficient Chinese corpus in the field of civil aviation air-ground calls can be solved, and the accuracy of civil aviation air-ground calls is improved.

Description

technical field [0001] The invention relates to the field of transfer learning, in particular to a speech recognition method based on transfer learning for the field of civil aviation, land and air calls. Background technique [0002] In recent years, the development of the national economy has promoted the continuous development of my country's civil aviation industry. While the number of flights has increased significantly, it has also put forward new tests for civil aviation safety. As an important communication method between pilots and air traffic controllers (hereinafter referred to as "controllers"), civil aviation ground-air dialogue has received unprecedented attention. From the point of view of civil aviation ground-air dialogue, on the basis of civil aviation communication equipment in service, in order to make aircraft operate safely and efficiently, controllers and pilots must accurately and clearly understand the voice intentions of both parties, so as to ensur...

AI Technical Summary

Problems solved by technology

In our country, an accident that happened at Urumqi Airport in Xinjiang in 1993 is still a lingering fear. The controller issued an instruction to set the altimeter to the correct value, but the pilot mistakenly treated it as the altitude value, which eventually led to the tragedy of aircraft crash and death.

After the incident, the investigation found that the controller's call language was not standardized and the pilot's misunderstanding was also the main cause of the flight crash.

[0004] In order to reduce ground-air dialogue errors, although the International Civil Aviation Organization and civil aviation management agencies of various countries have continuously improved the ground-air dialogue standards, flight accidents and accident symptoms caused by ground-air dialogue errors continue to occur

Images