一种音视结合的发音质量评估方法及系统
By combining visual and auditory modalities to assess facial movements and tongue position, this approach addresses the problem in existing technologies where pronunciation quality assessments cannot identify the underlying causes, thus enabling effective pronunciation correction guidance.
CN116649896BActive Publication Date: 2026-07-17INST OF COMPUTING TECH CHINESE ACAD OF SCI
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- INST OF COMPUTING TECH CHINESE ACAD OF SCI
- Filing Date
- 2023-04-28
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing pronunciation quality assessment methods mainly rely on audio modalities, which cannot effectively identify the causes of pronunciation non-standardities and lack visual modal information, thus failing to provide effective pronunciation correction suggestions.
Method used
By combining visual and auditory modalities, and measuring the standard of facial movements and tongue positions, this study assesses pronunciation quality and provides corrective suggestions using visual position indicators and audio formant frequency mapping.
Benefits of technology
It provides a comprehensive pronunciation quality assessment, can identify facial muscle movement and tongue position problems, and gives clear correction guidance to improve pronunciation accuracy.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116649896B_ABST
Abstract
本发明提出一种音视结合的发音质量评估方法，包括：采集标准发音状态下某一音位的标准音视频，获取该音位的标准视位和标准舌位；采集用户实际发音状态的该音位的实际音视频，获取该用户发出该音位的实际视位和实际舌位；分别将该实际视位与标准视位、该实际舌位与该标准舌位进行比对，得到该用户对该音位的发音偏差；基于该发音偏差生成矫正建议，并反馈给该用户进行发音矫正。本发明还提出一种音视结合的发音质量评估系统，以及一种用于用户发音质量评估的数据处理装置。
Need to check novelty before this filing date? Find Prior Art