This paper presents a new approach to estimate “universal” phoneme posterior probabilities for mixed language speech recognition. More specifically, we propose a new theoreti...
"The world of science and engineering is filled with signals: images from remote space probes, voltages generated by the heart and brain, radar and sonar echoes, seismic vibra...
Abstract. We report work on the mapping between the speech signal and articulatory trajectories from the MOCHA database. Contrasting previous works that used Neural Networks for th...
The REMOS (REverberation MOdeling for Speech recognition) concept for reverberation-robust distant-talking speech recognition, introduced in [1] for melspectral features, is exten...
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...