gmm.py 文件源码

def _transform_frame(self, src):
        """Mapping source spectral feature x to target spectral feature y
        so that minimize the mean least squared error.
        More specifically, it returns the value E(p(y|x)].

        Args:
            src (array): shape (`order of spectral feature`) source speaker's
                spectral feature that will be transformed

        Returns:
            array: converted spectral feature
        """
        D = len(src)

        # Eq.(11)
        E = np.zeros((self.num_mixtures, D))
        for m in range(self.num_mixtures):
            xx = np.linalg.solve(self.covarXX[m], src - self.src_means[m])
            E[m] = self.tgt_means[m] + self.covarYX[m].dot(xx)

        # Eq.(9) p(m|x)
        posterior = self.px.predict_proba(np.atleast_2d(src))

        # Eq.(13) conditinal mean E[p(y|x)]
        return posterior.dot(E).flatten()