This paper presents an efficient method for the conversion between subband domain representations of different filter banks. It advantageously replaces the conventional cascade of...
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
To make voice conversion usable in practical applications, the number of training sentences should be minimized. With traditional Gaussian mixture model (GMM) based techniques sma...
This paper presents a novel training method of an eigenvoice Gaussian mixture model (EV-GMM) effectively using non-parallel data sets for many-to-many eigenvoice conversion, which...
We have recently proposed an EM-style algorithm to optimize log-linear models with hidden variables. In this paper, we use this algorithm to optimize a hidden conditional random ï...
Georg Heigold, Stefan Hahn, Patrick Lehnen, Herman...