Edinburgh Research Explorer

Probabilistic Linear Discriminant Analysis with Bottleneck Features for Speech Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationINTERSPEECH-2014
PublisherInternational Speech Communication Association
Pages910-914
Number of pages5
Publication statusPublished - 2014

Abstract

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.

Download statistics

No data available

ID: 19957282