Please use this identifier to cite or link to this item:
Title: Experiments on acoustic model supervised adaptation and evaluation by K-Fold Cross Validation technique
Authors: Caon, Daniel R. S.
Amehraye, Asmaa
Razik, Joseph
Chollet, Gérard
Andreäo, Rodrigo V.
Mokbel, Chafic 
Affiliations: Department of Electrical Engineering 
Keywords: Hidden Markov models
Adaptation model
Data modeling
Electronic mail
Subjects: Databases
Issue Date: 2010
Part of: 2010 5th International Symposium On I/V Communications and Mobile Network
Start page: 1
End page: 4
Conference: International Symposium on I/V Communications and Mobile Network (5th : 30 Sep-2 Oct 2010 : Rabat, Morocco) 
This paper is an analysis of adaptation techniques for French acoustic models (hidden Markov models). The LVCSR engine Julius, the Hidden Markov Model Toolkit (HTK) and the K-Fold CV technique are used together to build three different adaptation methods: Maximum Likelihood a priori (ML), Maximum Likelihood Linear Regression (MLLR) and Maximum a posteriori (MAP). Experimental results by means of word and phoneme error rate indicate that the best adaptation method depends on the adaptation data, and that the acoustic models performance can be improved by the use of alignments at phoneme-level and K-Fold Cross Validation (CV). The very known K-Fold CV technique will point to the best adaptation technique to follow considering each case of data type.
Ezproxy URL: Link to full text
Type: Conference Paper
Appears in Collections:Department of Electrical Engineering

Show full item record

Record view(s)

checked on Jul 27, 2021

Google ScholarTM


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