Analysis of Hierarchical Bottleneck Framework for Improved Phoneme Recognition

Zaki, Mohammadi and Sailor, Hardik B and Patil, Hemant A (2016) Analysis of Hierarchical Bottleneck Framework for Improved Phoneme Recognition. In: 11th International Conference on Signal Processing and Communications (SPCOM), JUN 12-15, 2016, Indian Inst Sci, Banglore, INDIA.

PDF 2016_11th_Int_Con_Sig_Pro_Com_2016.pdf - Published Version Restricted to Registered users only Download (682kB) | Request a copy

Abstract

In this paper, an attempt is made to examine and evaluate the effect of bottleneck and the hierarchical bottleneck (HBN) framework in MLP-based Automatic Speech Recognition (ASR) systems. In particular, the bottleneck and hierarchical bottleneck framework are analyzed using Volterra series. Experiments on several architectures with incorporation of systematic hierarchical and bottleneck properties are done. We obtain significant increase in % Phone Recognition Accuracy (PRA) as compared to traditional cepstral features based Hidden Markov Model (HMM) acoustic modeling to more complex architectures such as the HBN framework. To this extent, the best results are achieved when tandem and acoustic features are combined in a deep HBN framework with 73.72 % PRA on entire TIMIT database. In addition, we observe a relative drop in dependence of language model (LM) on final % PRA with this proposed architecture.

Item Type:	Conference Proceedings
Additional Information:	Copy right for this article belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	31 Jan 2017 05:33
Last Modified:	31 Jan 2017 05:33
URI:	http://eprints.iisc.ac.in/id/eprint/56161

Actions (login required)

View Item