Language Identification using Acoustic Models and Speaker Compensated Cepstral-Time Matrices
Castaldo, F.
Dalmasso, E.
Laface, P.
Colibro, D.
Vair, C.
Politecnico di Torino;
This paper appears in: Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
Publication Date: 15-20 April 2007
Volume: 4,
On page(s): IV-1013-IV-1016
Location: Honolulu, HI,
ISSN: 1520-6149
ISBN: 1-4244-0727-3
INSPEC Accession Number: 9505957
Digital Object Identifier: 10.1109/ICASSP.2007.367244
Current Version Published: 2007-06-04
Abstract
This work presents two contributions to language identification. The first contribution is the definition of a set of properly selected time-frequency features that are a valid alternative to the commonly used shifted delta cepstral features. As a second contribution, we show that significant performance improvement in language recognition can be obtained estimating a subspace that represents the distortions due to inter-speaker variability within the same language, and compensating these distortions in the domain of the features. Experiments on the NIST 1996 and 2003 Language Recognition Evaluation data have been successfully used to validate the effectiveness of the proposed techniques
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
