Speech level evaluation method and system

Abstract

The invention provides a speech level evaluation method and system. The method comprises the steps of receiving speech voice data to be evaluated; conducting voice recognition on the speech voice data to obtain recognition text data; conducting characteristic extraction on the speech voice data and the recognition text data respectively to obtain speed evaluation characteristics. The speed evaluation characteristics comprise an acoustic speech evaluation characteristic and a semantic speech evaluation characteristic. According to the speed evaluation characteristics and a pre-constructed speech level evaluation model, evaluating the speech level of the speech voice data to obtain an evaluation result of the speech level. According to the speech level evaluation method, when the speech level is evaluated, no human participation is involved, therefore the practicability, the objectivity and the accuracy are improved, and the cost is lowered.

Description

technical field [0001] The present application relates to the technical field of natural language understanding and speech signal processing, and in particular, to a speech level evaluation method, device and system. Background technique [0002] As a way of disseminating information, speeches are widely used in all walks of life, such as in the field of education, speeches by education experts to help students improve their learning level and knowledge, and in research areas, speeches by domain experts can help research Speakers broaden their minds and expand their knowledge, and the content of speeches will benefit the audience a lot; however, some speakers do not perform well during the speech due to insufficient preparation or lack of their own professional knowledge, resulting in the content of the speech not being very good. good dissemination to the audience; and some speakers have high professional knowledge, can well disseminate the content of the speech to the audi...

AI Technical Summary

Problems solved by technology

[0002] As a way of disseminating information, speeches widely exist in all walks of life. For example, in the field of education, speeches by education experts can help students improve their learning level and knowledge. In the field of research, speeches by domain experts can help research The content of the speech will benefit the audience a lot; however, due to insufficient preparation or lack of professional knowledge, some speakers do not perform well during the speech process, resulting in the content of the speech not being very good. Good dissemination to the audience; and some speakers have high professional knowledge, can disseminate the speech content to the audience well, and let the audience remember deeply; it can be seen that the level of the speaker's speech is directly related to the dissemination of the speech content How to objectively evaluate the speaker's speech level is of great significance

[0003] In related technologies, speech level evaluation methods generally require humans to listen to speech speech data or watch speech videos to give the evaluation results of the speaker's speech level. The humans are generally experts or professionals. The workload of the method is large, the cost is high, and it is not practical. In addition, the manual evaluation of the speaker's speech level has a certain degree of subjectivity, which is unfair to the evaluated person.

Images