Voice conversion can be reduced to a problem to find a transformation function between the corresponding speech sequences of two speakers. Perhaps the most voice conversions meth...
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
In this paper, a single antenna downlink channel with K users is analyzed in the presence of Rayleigh flat fading. A limited channel state information (CSI) feedback scheme is co...
Preparation of a lexicon for speech recognition systems can be a significant effort in languages where the written form is not exactly phonetic. On the other hand, in languages w...
Nagendra Goel, Samuel Thomas, Mohit Agarwal, Pinar...
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...