15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

Probabilistic Linear Discriminant Analysis with Bottleneck Features for Speech Recognition

Liang Lu, Steve Renals

University of Edinburgh, UK

We have recently proposed a new acoustic model based on probabilistic linear discriminant analysis (PLDA) which enjoys the flexibility of using higher dimensional acoustic features, and is more capable to capture the intra-frame feature correlations. In this paper, we investigate the use of bottleneck features obtained from a deep neural network (DNN) for the PLDA-based acoustic model. Experiments were performed on the Switchboard dataset — a large vocabulary conversational telephone speech corpus. We observe significant word error reduction by using the bottleneck features. In addition, we have also compared the PLDA-based acoustic model to three others using Gaussian mixture models (GMMs), subspace GMMs and hybrid deep neural networks (DNNs), and PLDA can achieve comparable or slightly higher recognition accuracy from our experiments.

Full Paper

Bibliographic reference.  Lu, Liang / Renals, Steve (2014): "Probabilistic linear discriminant analysis with bottleneck features for speech recognition", In INTERSPEECH-2014, 910-914.