Speech recognition method suitable for noise environment
A speech recognition and noise technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as the decline of recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0085] Such as figure 1 As shown, a speech recognition method suitable for noise environment, including the following steps:
[0086] 1) by such as figure 2 The shown dual-microphone array model collects speech signals, and establishes the following formal model for the collected speech signals:
[0087] the y m (t)=x m (t)+n m (t) m=1,2,...,M (1)
[0088] In the above formula (1), M represents the number of microphones, and x m (t) represents a pure speech signal, n m (t) represents additive noise and interference signal, y m (t) represents a noisy speech signal;
[0089] 2) Carry out Fourier transform to the noisy speech signal that step 1) gathers, obtain frequency domain, frequency domain expression is:
[0090] Y(l,k)=X(l,k)+N(l,k) (2)
[0091] In the above formula (2), Y(l,k) is the spectrum of the noisy speech signal, X(l,k) is the spectrum of the original pure speech signal, N(l,k) is the spectrum of the noise signal, l is the time index, k is the frequency...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com