Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >

Please use this identifier to cite or link to this item:

This item has been viewed 9 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
frankel_AF-MLP.pdf98.49 kBAdobe PDFView/Open
Title: Articulatory feature classifiers trained on 2000 hours of telephone speech
Authors: Frankel, Joe
Magimai-Doss, Mathew
King, Simon
Livescu, Karen
Çetin, Ozgur
Issue Date: 2007
Citation: J. Frankel, M. Magimai-Doss, S. King, K. Livescu, and O. Çetin. Articulatory feature classifiers trained on 2000 hours of telephone speech. In Proc. Interspeech, Antwerp, Belgium, August 2007.
Abstract: The so-called tandem approach, where the posteriors of a multilayer perceptron (MLP) classifier are used as features in an automatic speech recognition (ASR) system has proven to be a very effective method. Most tandem approaches up to date have relied on MLPs trained for phone classification, and appended the posterior features to some standard feature hidden Markov model (HMM). In this paper, we develop an alternative tandem approach based on MLPs trained for articulatory feature (AF) classification. We also develop a factored observation model for characterizing the posterior and standard features at the HMM outputs, allowing for separate hidden mixture and state-tying structures for each factor. In experiments on a subset of Switchboard, we show that the AFbased tandem approach is as effective as the phone-based approach, and that the factored observation model significantly outperforms the simple feature concatenation approach while using fewer parameters.
Keywords: speech technology
Appears in Collections:CSTR publications
Linguistics and English Language publications

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy