I propose an acoustic model adaptation method using bases constructed through the sparse principal component analysis (SPCA) of acoustic models trained in a clean environment. I perform experiments on adaptation to a new speaker and noise. The SPCA-based method outperforms the PCA-based method in the presence of babble noise.
Yongwon JEONG
Pusan National University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yongwon JEONG, "Speaker Adaptation in Sparse Subspace of Acoustic Models" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 6, pp. 1402-1405, June 2013, doi: 10.1587/transinf.E96.D.1402.
Abstract: I propose an acoustic model adaptation method using bases constructed through the sparse principal component analysis (SPCA) of acoustic models trained in a clean environment. I perform experiments on adaptation to a new speaker and noise. The SPCA-based method outperforms the PCA-based method in the presence of babble noise.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E96.D.1402/_p
Copy
@ARTICLE{e96-d_6_1402,
author={Yongwon JEONG, },
journal={IEICE TRANSACTIONS on Information},
title={Speaker Adaptation in Sparse Subspace of Acoustic Models},
year={2013},
volume={E96-D},
number={6},
pages={1402-1405},
abstract={I propose an acoustic model adaptation method using bases constructed through the sparse principal component analysis (SPCA) of acoustic models trained in a clean environment. I perform experiments on adaptation to a new speaker and noise. The SPCA-based method outperforms the PCA-based method in the presence of babble noise.},
keywords={},
doi={10.1587/transinf.E96.D.1402},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Speaker Adaptation in Sparse Subspace of Acoustic Models
T2 - IEICE TRANSACTIONS on Information
SP - 1402
EP - 1405
AU - Yongwon JEONG
PY - 2013
DO - 10.1587/transinf.E96.D.1402
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2013
AB - I propose an acoustic model adaptation method using bases constructed through the sparse principal component analysis (SPCA) of acoustic models trained in a clean environment. I perform experiments on adaptation to a new speaker and noise. The SPCA-based method outperforms the PCA-based method in the presence of babble noise.
ER -