Method and device for noise suppression, phonetic feature extraction, speech recognition and training voice model
A technology for noise suppression and speech features, which is applied in the field of noise suppression of speech spectrum, and can solve the problem of a large amount of calculation of the gain function.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] In order to facilitate the understanding of the following embodiments, the principles of minimum mean square error (MMSE) estimation and log spectrum minimum mean square error (LogMMSE) estimation are briefly introduced first.
[0035] MMSE estimation is a speech enhancement algorithm, which uses the estimated spectrum of background noise to suppress the noise in the noisy speech spectrum to obtain the speech spectrum with noise suppressed. Specifically, the minimum mean square error estimation is performed by the following formula:
[0036] y(t)=x(t)+d(t), 0≤t≤T (1)
[0037] A ^ k = E { A k | y ( t ) , 0 ≤ t ≤ T } - - - ( 2 )
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 