Home >

news Help

Publication Information


Title
Japanese: 
English:Optimizing Speaker Embeddings using Meta-Training Sets 
Author
Japanese: 井上中順, Goto Keita.  
English: Nakamasa Inoue, Keita Goto.  
Language English 
Journal/Book name
Japanese: 
English:2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 
Volume, Number, Page         pp. 600-604
Published date Dec. 31, 2020 
Publisher
Japanese: 
English:IEEE 
Conference name
Japanese: 
English:Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2020（APSIPA ASC） 
Conference site
Japanese: 
English: 
Official URL http://www.apsipa.org/proceedings/2020/APSIPA-ASC-2020.html
 
Abstract This paper presents a method to learn speaker em- beddings for text-independent speaker verification. The proposed method aims to optimize embeddings for unseen enrollment/test speakers by training a network with a meta-training set. The main procedure consists of two steps. The first step generates a meta-training set, a set of episodes each with a pair of intra- episode training and testing sets. The second step optimizes network parameters so that the average verification performance over the generated episodes is maximized. An advantage of our approach lies in its complementarity to studies focusing on network structure and we demonstrate its effectiveness with recent ResNet-based models in experiments on the VoxCeleb dataset.

©2007 Tokyo Institute of Technology All rights reserved.