Interspeech 2019 2019
DOI: 10.21437/interspeech.2019-1230
|View full text |Cite
|
Sign up to set email alerts
|

The DKU Replay Detection System for the ASVspoof 2019 Challenge: On Data Augmentation, Feature Representation, Classification, and Fusion

Abstract: This paper describes our DKU replay detection system for the ASVspoof 2019 challenge. The goal is to develop spoofing countermeasure for automatic speaker recognition in physical access scenario. We leverage the countermeasure system pipeline from four aspects, including the data augmentation, feature representation, classification, and fusion. First, we introduce an utterance-level deep learning framework for antispoofing. It receives the variable-length feature sequence and outputs the utterance-level scores… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
45
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 55 publications
(45 citation statements)
references
References 31 publications
0
45
0
Order By: Relevance
“…From Eqs. (18) and (19), we can see that F mro is determined by F vrs and then F vrs is determined by σ 2 X , σ 2 Y , X, and Y . However, as these parameters are unknown, it is not possible to determine the value of F 1 and F 2 directly.…”
Section: Variance-based Modified Log Magnitude Spectrummentioning
confidence: 85%
See 4 more Smart Citations
“…From Eqs. (18) and (19), we can see that F mro is determined by F vrs and then F vrs is determined by σ 2 X , σ 2 Y , X, and Y . However, as these parameters are unknown, it is not possible to determine the value of F 1 and F 2 directly.…”
Section: Variance-based Modified Log Magnitude Spectrummentioning
confidence: 85%
“…According to the relationship between F mro and F vrs in Eqs. (18) and (19), we can know that the statistics value of F mro is above 1 on the two databases. Further, we can know that F X Y is larger than F XY .…”
Section: Variance-based Modified Log Magnitude Spectrummentioning
confidence: 92%
See 3 more Smart Citations