Huawei technologies co., ltd. (20240096343). VOICE QUALITY ENHANCEMENT METHOD AND RELATED DEVICE simplified abstract
Contents
VOICE QUALITY ENHANCEMENT METHOD AND RELATED DEVICE
Organization Name
Inventor(s)
Shiqiang Peng of Shenzhen (CN)
VOICE QUALITY ENHANCEMENT METHOD AND RELATED DEVICE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240096343 titled 'VOICE QUALITY ENHANCEMENT METHOD AND RELATED DEVICE
Simplified Explanation
The patent application relates to a voice quality enhancement method using artificial intelligence, specifically focusing on noise reduction in voice signals.
- The method involves enabling a PNR mode to obtain a noisy voice signal and target voice-related data, performing noise reduction on the noisy voice signal based on the target voice-related data using a trained voice noise reduction model, and obtaining a noise-reduced voice signal of the target user.
Potential Applications: - Telecommunications industry for improving call quality - Voice recognition software for better accuracy
Problems Solved: - Enhancing voice quality in noisy environments - Improving user experience in voice communication
Benefits: - Clearer voice signals for better communication - Reduction of interference for improved user satisfaction
Potential Commercial Applications: Improving Voice Quality in Telecommunications with AI-Based Noise Reduction
Possible Prior Art: Prior art may include noise reduction algorithms used in audio processing software or hardware.
Unanswered Questions: 1. How does the method handle different types of noise in voice signals? 2. What is the computational complexity of implementing the trained voice noise reduction model?
Original Abstract Submitted
this application relates to the artificial intelligence (ai) field, and specifically, to a voice quality enhancement method and a related device. the method includes: after a pnr mode is enabled, obtaining a noisy voice signal and target voice-related data, where the noisy-carrying voice signal includes a voice signal of a target user and an interfering noise signal, and the target voice-related data indicates a voice feature of the target user; and performing noise reduction on the noisy voice signal based on the target voice-related data by using a trained voice noise reduction model to obtain a noise-reduced voice signal of the target user, where the voice noise reduction model is implemented based on a neural network. in embodiments of this application, voice of a target person can be enhanced, and interference can be suppressed.
- Huawei technologies co., ltd.
- Shanyi Wei of Shenzhen (CN)
- Chao Wu of Hangzhou (CN)
- Yan Qiu of Hangzhou (CN)
- Meng Liao of Hangzhou (CN)
- Fan Fan of Shenzhen (CN)
- Shiqiang Peng of Shenzhen (CN)
- Bin Li of Shenzhen (CN)
- Wenbin Zhao of Moscow (RU)
- Jiang Li of Shenzhen (CN)
- Haiting Li of Beijing (CN)
- Xueyan Huang of Shenzhen (CN)
- G10L21/0232
- G10L21/0308