Method for testing rhythm level of spoken English

Abstract

The invention discloses a method for testing the rhythm level of spoken English. The method comprises the following steps of: A, preprocessing an original English speech signal; B, extracting multi-knowledge-source characteristic parameters used for a rhythm test from the preprocessed original English speech signal, wherein the multi-knowledge-source characteristic parameters comprise rhythm performance characteristics, rhythm generation characteristics and rhythm influence characteristics; and C, acquiring a rhythm level test score of original English sounds by using most of the multi-knowledge-source characteristic parameters. By the method for testing the rhythm level of spoken English, a better test result is obtained by using a strategy in which multi-knowledge information is used for thinning and merging, and the objectivity and the accuracy of the test are improved.

Description

technical field [0001] The invention relates to the technical field of voice signal processing and pattern recognition in the artificial intelligence industry, in particular to a method for testing the prosody level of spoken English. Background technique [0002] Prosody is proposed for speech, which is a human behavior. The medium of speech communication is sound, so the information that the speaker wants to convey and the information that the listener can hear are all contained in the sound wave. In computer-aided language learning, prosodic performance is like the "elegance" in the language learners' expression realm of "faithfulness, expressiveness, elegance". It is the most advanced link in speech, and it acts on speech through complex physical and acoustic patterns. , to characterize the suprasegmental characteristics of the speaker such as tone, attitude, intention and emotion. It can be said that in the process of expression, just being able to read does not necess...

AI Technical Summary

Problems solved by technology

[0006] Existing prosody testing methods generally use pure fundamental frequency, duration, and energy features directly, without in-depth processing of the features themselves, and without targeted introduction of multi-knowledge related to prosody performance, prosody production, and prosody influence. source model

However, a large number of research practices in the field of educational measurement and pattern recognition have shown that it is difficult to further improve test performance by simply using prosodic features.

Images