Convolutive Bottleneck Network features for LVCSR

  title={Convolutive Bottleneck Network features for LVCSR},
  author={Karel Vesel{\'y} and Martin Karafi{\'a}t and Frantisek Gr{\'e}zl},
  journal={2011 IEEE Workshop on Automatic Speech Recognition & Understanding},
In this paper, we focus on improvements of the bottleneck ANN in a Tandem LVCSR system. First, the influence of training set size and the ANN size is evaluated. Second, a very positive effect of linear bottleneck is shown. Finally a Convolutive Bottleneck Network is proposed as extension of the current state-of-the-art Universal Context Network. The proposed training method leads to 5.5% relative reduction of WER, compared to the Universal Context ANN baseline. The relative improvement compared… CONTINUE READING
Highly Cited
This paper has 102 citations. REVIEW CITATIONS

10 Figures & Tables



Citations per Year

102 Citations

Semantic Scholar estimates that this publication has 102 citations based on the available data.

See our FAQ for additional information.