Pronunciation detection method and apparatus, and phonetic-category learning method and system

Abstract

The invention, which relates to the field of the computer technology, provides a pronunciation detection method. The method comprises: collecting a speech signal that is generated when a tested personreads a designated content and a vibration intensity at a specific position outside a vocal organ; according to the speech signal, acquiring a vibration intensity corresponding to a to-be-tested pronunciation in the designated content; and on the basis of a relationship between the vibration intensity corresponding to the to-be-tested pronunciation and a threshold, determining whether the to-be-tested pronunciation is correct. According to the invention, on the basis of non-invasive pronunciation detection, the operation becomes simple and the cost is lowered; and the tested person feels safeand comfortable. Besides, the invention also provides a pronunciation detection apparatus and a phonetic-category learning method and system based on the pronunciation detection method.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for pronouncing detection, and a method and system for learning a pronunciation category. Background technique [0002] The acquisition of phonemic categories is a difficult problem in phonetic rehabilitation, second language acquisition, and dialect native speakers learning the common language of the nation. [0003] Taking the nasal n and lateral l in Mandarin Chinese as an example, native speakers of dialects in a large area of ​​southern my country have great difficulties in separating the two. Therefore, it is of high application value to develop a practical method and system for phoneme category acquisition to help people with difficulties distinguish between confused phoneme categories. [0004] At present, the acquisition training of the phoneme category mainly includes the following forms: correct pronunciation exercises in the pronunciation traini...

AI Technical Summary

Problems solved by technology

[0006] However, this intrusive pronunciation action detection method and the pronunciation training method based on the intrusive pronunciation action detection, in addition to being expensive and inconvenient to operate, also have the following obvious disadvantages:

[0007] (1) Intrusive pronunciation movement detection methods require a large number of advanced sensors with smaller volumes to detect organ movements, which makes the cost high and difficult to promote;

[0008] (2) Intrusive pronunciation movement detection means, because the sensor needs to go deep into the vocal tract of the subject, it may cause physiological discomfort to the subject, thereby affecting their normal pronunciation;

[0009] (3) For some specific phonemes, due to the complexity of the pronunciation action, the pronunciation part is too deep, etc., it is difficult to achieve detection even with intrusive means

Images