Federated Acoustic Model Optimization for Automatic Speech Recognition

被引：4

作者：

Tan, Conghui ^{[1
]}

Jiang, Di ^{[1
]}

Mo, Huaxiao ^{[1
]}

Peng, Jinhua ^{[1
]}

Tong, Yongxin ^{[2
,3
]}

Zhao, Weiwei ^{[1
]}

Chen, Chaotao ^{[1
]}

Lian, Rongzhong ^{[1
]}

Song, Yuanfeng ^{[1
]}

Xu, Qian ^{[1
]}

机构：

[1] WeBank Co Ltd, AI Grp, Shenzhen, Peoples R China

[2] Beihang Univ, SKLSDE Lab, BDBC, Beijing, Peoples R China

[3] Beihang Univ, IRI, BDBC, Beijing, Peoples R China

来源：

DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2020), PT III | 2020年 / 12114卷

关键词：

Automatic Speech Recognition; Federated learning;

D O I：

10.1007/978-3-030-59419-0_54

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Traditional Automatic Speech Recognition (ASR) systems are usually trained with speech records centralized on the ASR vendor's machines. However, with data regulations such as General Data Protection Regulation (GDPR) coming into force, sensitive data such as speech records are not allowed to be utilized in such a centralized approach anymore. In this demonstration, we propose and show the method of federated acoustic model optimization in order to solve this problem. This demonstration does not only vividly show the underlying working mechanisms of the proposed method but also provides an interface for the user to customize its hyperparameters. With this demonstration, the audience can experience the effect of federated learning in an interactive fashion and we wish this demonstration would inspire more research on GDPR-compliant ASR technologies.

引用

页码：771 / 774

页数：4

共 6 条

[1] [Anonymous], 2002, P ICSLP
[2] Huang Y, 2014, INTERSPEECH, P845
[3] Konečny J, 2017, Arxiv, DOI arXiv:1610.05492
[4] Mitchell M, 1998, INTRO GENETIC ALGORI
[5] Povey D., 2011, PROC IEEE 2011 WORKS
[6] Federated Machine Learning: Concept and Applications
Yang, Qiang
Liu, Yang
Chen, Tianjian
Tong, Yongxin
[J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2019, 10 (02)

← 1 →