Convolutive Bottleneck Network features for LVCSR | IEEE Conference Publication | IEEE Xplore

Convolutive Bottleneck Network features for LVCSR


Abstract:

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...Show More

Abstract:

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 to the 5-layer single-bottleneck network is 17.7%. The dataset ctstrain07 composed of more than 2000 hours of English Conversational Telephone Speech was used for the experiments. The TNet toolkit with CUDA GPGPU implementation was used for fast training.
Date of Conference: 11-15 December 2011
Date Added to IEEE Xplore: 05 March 2012
ISBN Information:
Conference Location: Waikoloa, HI, USA

References

References is not available for this document.