Loading...
Please wait, while we are loading the content...
Similar Documents
Method for Speech Recognition Using Uncertainty Information for Sub-bands in Noise Environment and Apparatus Thereof Cross-reference to Related Application
| Content Provider | Semantic Scholar |
|---|---|
| Copyright Year | 2017 |
| Abstract | According to a method and apparatus for speech recognition in noise environment of the present invention using uncer tainty information for Sub-band, uncertainty information of each Sub-band is extracted from estimated clean speech using noise modeling, and helps to extract speech features that are robust to noise using the extracted uncertainty information as a weight with respect to each Sub-band. Also, an acoustic model is converted according to each Sub-band weight, and speech recognition is performed based on the converted acoustic model and the extracted speech features. As a result, while the noise modeling over time is not so accurate, noise influence resulted from Sub-bands having high corruption can be reduced according to the uncertainty information of the corresponding Sub-band, and speech recognition perfor mance in complex noise environments can be improved. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://patentimages.storage.googleapis.com/66/61/8e/b0382d5de45efa/US20090076813A1.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Patent |
