Speech enhancement method for speech recognition in noise environment
A speech enhancement and speech recognition technology, applied in speech recognition, speech analysis, instruments, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0069] Examples:
[0070] Such as figure 1 As shown, a speech enhancement method applied to speech recognition in a noisy environment is to construct an MVDR beamformer based on time-frequency masking, and post an improved Wiener filter to perform speech enhancement processing on the target sound source direction. Including the following steps:
[0071] 1) The four-element microphone array model is used to receive the voice signal, and the time domain of the noisy voice signal received by the microphone array is expressed as: y m (t)=s m (t)+n m (t), m = 1, 2, ... M, where M represents the number of microphones, s m (t) represents a pure voice signal, n m (t) represents the interference noise signal;
[0072] 2) Perform short-time Fourier transform on the noisy speech signal received in step 1), and obtain the time-frequency domain signal in the form of Y m (f,t)=S m (f,t)+N m (f,t), where Y m (f,t), S m (f,t), N m (f, t) respectively represent the signal at time t, frequency f, targ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap