Spoken language recognition and correction system

Abstract

The invention provides a spoken language recognition and correction system. According to the system, multichannel enhancement and noise reduction are performed on the received spoken language voice signals, then extraction of combined characteristic parameters is performed on analog signals after enhancement and noise reduction, the combined characteristic parameters are converted into optimized characteristic parameters through self-adaptive conversion and parameter conversion, and finally the optimized characteristic parameters are matched with the standard spoken language data in a standard library so that spoken language correction output is completed. A series of signal conversion is performed on the spoken language input information of students so that the students possibly having nonstandard accent are enabled to follow the system to perform spoken language learning and correction through the conversion and matching functions of the system.

Description

technical field [0001] The invention belongs to the technical field of speech signal processing, and in particular relates to a spoken language recognition correction system. Background technique [0002] As an important medium of interpersonal communication, spoken language plays an extremely important role in real life. With the continuous development of social economy and the intensification of globalization, people have put forward higher and higher requirements for the efficiency of language learning and the objectivity, fairness and scale of test of language assessment. The traditional artificial oral English assessment method greatly limits the teaching time and space for teachers and students, and there are also many hardware gaps and imbalances in terms of teaching staff, teaching venues, and expenditures; manual assessment cannot avoid evaluators Due to individual deviations, the uniformity of the scoring standards cannot be guaranteed, and sometimes it cannot eve...

AI Technical Summary

Problems solved by technology

However, in practical applications, especially for large-scale oral examinations or oral English training in other public places, the recording environment will inevitably be affected by factors such as the noise of the examination room and the environment. Proportional anomaly scoring speech

Obviously, this phenomenon makes it difficult for computers to automatically score in large-scale oral exams, which limits oral learning.

Images