Investigation into bottle-neck features for meeting speech recognition

This work investigates into recently proposed Bottle-Neck features for ASR. The bottle-neck ANN structure is imported into Split Context architecture gaining significant WER reduction. Further, Universal Context architecture was developed which simplifies the system by using only one universal ANN for all temporal splits. Significant WER reduction can be obtained by applying fMPE on top of our BN features as a technique for discriminative feature extraction and further gain is also obtained by retraining model parameters using MPE criterion. The results are reported on meeting data from RT07 evaluation.