Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS

Abstract: 

The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises concerns about the privacy and security issues. The recognition results generated in cloud may also reveal some sensitive information. This paper proposes a deep polynomial network (DPN) that can be applied to the encrypted speech as an acoustic model. It allows clients to send their data in an encrypted form to the cloud to ensure that their data remains confidential, at mean while the DPN can still make frame-level predictions over the encrypted speech and return them in encrypted form. One good property of the DPN is that it can be trained on unencrypted speech features in the traditional way. To keep the cloud away from the raw audio and recognition results, a cloud-local joint decoding framework is also proposed. We demonstrate the effectiveness of model and framework on the Switchboard and Cortana voice assistant tasks with small performance degradation and latency increased comparing with the traditional cloud-based DNNs.

up
0 users have voted:

Paper Details

Authors:
Yifan Gong, Dong YU
Submitted On:
8 May 2019 - 4:21am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Dong YU
Paper Code:
SLP-L3.3
Document Year:
2019
Cite

Document Files

Encrypted_ASR

(43)

Subscribe

[1] Yifan Gong, Dong YU, " ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4045. Accessed: Nov. 15, 2019.
@article{4045-19,
url = {http://sigport.org/4045},
author = {Yifan Gong; Dong YU },
publisher = {IEEE SigPort},
title = { ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS},
year = {2019} }
TY - EJOUR
T1 - ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS
AU - Yifan Gong; Dong YU
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4045
ER -
Yifan Gong, Dong YU. (2019). ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS. IEEE SigPort. http://sigport.org/4045
Yifan Gong, Dong YU, 2019. ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS. Available at: http://sigport.org/4045.
Yifan Gong, Dong YU. (2019). " ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS." Web.
1. Yifan Gong, Dong YU. ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4045