From: Grid-based approximation for voice conversion in low resource environments
Input: a sequence of states sampled from the observed process x 1:T |
Initialization: set the initial weights, \(\left \{w_{0|0}^{k}\right \}_{k=1}^{N_{y}}\), using Eq. (13) |
Main iteration: for t=1,…T, perform the following steps: |
1. Evaluate the prior weights, \(\left \{w_{t|t-1}^{k}\right \}_{k=1}^{N_{y}}\), using Eq. (10). |
2. Evaluate the posterior weights, \(\left \{w_{t|t}^{k}\right \}_{k=1}^{N_{y}}\), using Eq. (11). |
3. Evaluate the hidden state, \(\hat {\mathbf {y}}_{t}\), using Eq. (12). |
Output: a sequence of the estimated hidden states \({\hat {\mathbf {y}}_{1:T}}\) |