Title :
Towards better capturing inter-speaker information by active learning for speaker identification
Author :
Wang, Lan ; Chen, Ke ; Chi, Hui Sheng
Author_Institution :
Nat. Lab. of Machine Perception, Peking Univ., Beijing, China
Abstract :
In our previous work (2000), we proposed a novel way to capture inter-speaker information with a neural network for speaker identification system. 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
Keywords :
generalisation (artificial intelligence); learning (artificial intelligence); neural nets; speaker recognition; KING speech corpus; active learning algorithm; generalization; interspeaker information capturing; neural network; speaker recognition; Forensics; Hidden Markov models; Human voice; Information science; Laboratories; Loudspeakers; Machine learning; Narrowband; Neural networks; Speech;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938851