Towards better capturing inter-speaker information by active learning for speaker identification

L. Wang; K. Chen; H. S. Chi

Towards better capturing inter-speaker information by active learning for speaker identification

L. Wang, K. Chen, H. S. Chi

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

In our previous work, we proposed a novel way to capture inter-speaker information with a neural network for speaker identification system [1]. In this paper, an active learning algorithm is presented for improving the generalization ability of the neural network towards better capturing inter-speaker information. Comparative results on the KING speech corpus show that our method leads to a considerable improvement, in particular, for the narrow-band set.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks\|Proc Int Jt Conf Neural Networks
Publisher	IEEE
Pages	2975-2980
Number of pages	5
Volume	4
Publication status	Published - 2001
Event	International Joint Conference on Neural Networks (IJCNN'01) - Washington, DC Duration: 1 Jul 2001 → …

Conference

Conference	International Joint Conference on Neural Networks (IJCNN'01)
City	Washington, DC
Period	1/07/01 → …

Cite this

@inproceedings{7d18425df2674c16acf83606ee081527,

title = "Towards better capturing inter-speaker information by active learning for speaker identification",

abstract = "In our previous work, we proposed a novel way to capture inter-speaker information with a neural network for speaker identification system [1]. In this paper, an active learning algorithm is presented for improving the generalization ability of the neural network towards better capturing inter-speaker information. Comparative results on the KING speech corpus show that our method leads to a considerable improvement, in particular, for the narrow-band set.",

author = "L. Wang and K. Chen and Chi, {H. S.}",

year = "2001",

language = "English",

volume = "4",

pages = "2975--2980",

booktitle = "Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks",

publisher = "IEEE",

address = "United States",

note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 01-07-2001",

}

TY - GEN

T1 - Towards better capturing inter-speaker information by active learning for speaker identification

AU - Wang, L.

AU - Chen, K.

AU - Chi, H. S.

PY - 2001

Y1 - 2001

N2 - In our previous work, we proposed a novel way to capture inter-speaker information with a neural network for speaker identification system [1]. In this paper, an active learning algorithm is presented for improving the generalization ability of the neural network towards better capturing inter-speaker information. Comparative results on the KING speech corpus show that our method leads to a considerable improvement, in particular, for the narrow-band set.

AB - In our previous work, we proposed a novel way to capture inter-speaker information with a neural network for speaker identification system [1]. In this paper, an active learning algorithm is presented for improving the generalization ability of the neural network towards better capturing inter-speaker information. Comparative results on the KING speech corpus show that our method leads to a considerable improvement, in particular, for the narrow-band set.

M3 - Conference contribution

VL - 4

SP - 2975

EP - 2980

BT - Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks

PB - IEEE

T2 - International Joint Conference on Neural Networks (IJCNN'01)

Y2 - 1 July 2001

ER -

Towards better capturing inter-speaker information by active learning for speaker identification

Abstract

Conference

Fingerprint

Cite this