Matches in SemOpenAlex for { <https://semopenalex.org/work/W2471406290> ?p ?o ?g. }
- W2471406290 abstract "All methods analyzed and contrasted in this chapter have the unique attribute of exploiting prior knowledge about distortion in the training stage, in addition to training an HMM. They then use such prior knowledge as a guide to either remove noise or adapt models in the testing or deployment stage. Most methods which use prior knowledge about acoustic distortions as discussed in this chapter learn the nonlinear mapping functions between the clean and noisy speech features when they are available in the training phase as a pair of stereo data. By modeling the differences between the features or models of the stereo data, a distortion model can be learned accurately in training and subsequently used in testing to perform feature enhancement or model compensation. Another set of methods that also exploit prior knowledge operate by collecting and learning a set of simple models first, each corresponding to one specific acoustic environment in the training. These environment-specific models are then combined in the online fashion to form a new acoustic model that is aimed to fit the test environment in an optimal manner." @default.
- W2471406290 created "2016-07-22" @default.
- W2471406290 creator A5029670581 @default.
- W2471406290 creator A5035017068 @default.
- W2471406290 creator A5077401426 @default.
- W2471406290 creator A5082075598 @default.
- W2471406290 date "2016-01-01" @default.
- W2471406290 modified "2023-10-18" @default.
- W2471406290 title "Compensation with prior knowledge" @default.
- W2471406290 cites W1279245896 @default.
- W2471406290 cites W130397547 @default.
- W2471406290 cites W146976060 @default.
- W2471406290 cites W1485038873 @default.
- W2471406290 cites W1513820424 @default.
- W2471406290 cites W1567690964 @default.
- W2471406290 cites W1598508708 @default.
- W2471406290 cites W1602032261 @default.
- W2471406290 cites W180035620 @default.
- W2471406290 cites W1831449718 @default.
- W2471406290 cites W1843554590 @default.
- W2471406290 cites W1877570817 @default.
- W2471406290 cites W1950777589 @default.
- W2471406290 cites W1958042395 @default.
- W2471406290 cites W1958409774 @default.
- W2471406290 cites W1973681148 @default.
- W2471406290 cites W1988052084 @default.
- W2471406290 cites W1988541906 @default.
- W2471406290 cites W1993492867 @default.
- W2471406290 cites W1997063331 @default.
- W2471406290 cites W2013608223 @default.
- W2471406290 cites W2031647436 @default.
- W2471406290 cites W2032243055 @default.
- W2471406290 cites W2035576074 @default.
- W2471406290 cites W2036635146 @default.
- W2471406290 cites W2042141988 @default.
- W2471406290 cites W2046869671 @default.
- W2471406290 cites W2062164080 @default.
- W2471406290 cites W2063291689 @default.
- W2471406290 cites W2066674745 @default.
- W2471406290 cites W2069631319 @default.
- W2471406290 cites W2069681747 @default.
- W2471406290 cites W2077541282 @default.
- W2471406290 cites W2094461119 @default.
- W2471406290 cites W2096055753 @default.
- W2471406290 cites W2096170322 @default.
- W2471406290 cites W2097427452 @default.
- W2471406290 cites W2103537425 @default.
- W2471406290 cites W2104298926 @default.
- W2471406290 cites W2112909784 @default.
- W2471406290 cites W2113911479 @default.
- W2471406290 cites W2113981416 @default.
- W2471406290 cites W2115055618 @default.
- W2471406290 cites W2116496426 @default.
- W2471406290 cites W2118595744 @default.
- W2471406290 cites W2122140124 @default.
- W2471406290 cites W2124149378 @default.
- W2471406290 cites W2125562481 @default.
- W2471406290 cites W2125610823 @default.
- W2471406290 cites W2126336864 @default.
- W2471406290 cites W2134218976 @default.
- W2471406290 cites W2135029798 @default.
- W2471406290 cites W2135046866 @default.
- W2471406290 cites W2136466519 @default.
- W2471406290 cites W2141520175 @default.
- W2471406290 cites W2141623350 @default.
- W2471406290 cites W2143044285 @default.
- W2471406290 cites W2144521324 @default.
- W2471406290 cites W2150415460 @default.
- W2471406290 cites W2150863656 @default.
- W2471406290 cites W2153270237 @default.
- W2471406290 cites W2154920538 @default.
- W2471406290 cites W2157178676 @default.
- W2471406290 cites W2158291955 @default.
- W2471406290 cites W2165108269 @default.
- W2471406290 cites W2168076624 @default.
- W2471406290 cites W2168379380 @default.
- W2471406290 cites W2290318471 @default.
- W2471406290 cites W2397558578 @default.
- W2471406290 cites W2402267837 @default.
- W2471406290 cites W2403608536 @default.
- W2471406290 cites W2403766732 @default.
- W2471406290 cites W2404151332 @default.
- W2471406290 cites W2405589348 @default.
- W2471406290 cites W2405716592 @default.
- W2471406290 cites W2405774341 @default.
- W2471406290 cites W2407935965 @default.
- W2471406290 cites W2408713104 @default.
- W2471406290 cites W3141839452 @default.
- W2471406290 cites W33099690 @default.
- W2471406290 cites W36000887 @default.
- W2471406290 cites W84880661 @default.
- W2471406290 cites W2401131605 @default.
- W2471406290 doi "https://doi.org/10.1016/b978-0-12-802398-3.00005-2" @default.
- W2471406290 hasPublicationYear "2016" @default.
- W2471406290 type Work @default.
- W2471406290 sameAs 2471406290 @default.
- W2471406290 citedByCount "0" @default.
- W2471406290 crossrefType "book-chapter" @default.
- W2471406290 hasAuthorship W2471406290A5029670581 @default.
- W2471406290 hasAuthorship W2471406290A5035017068 @default.