A DISCRIMINATIVE APPROACH FOR SPEAKER SELECTION IN SPEAKER DE-IDENTIFICATION SYSTEMS

被引：0

作者：

Abou-Zleikha, Mohamed ^{[1
,2
]}

Tan, Zheng-Hua ^{[2
]}

Christensen, Mads Graesboll ^{[1
]}

Jensen, Soren Holdt ^{[2
]}

机构：

[1] Aalborg Univ, AD MT, Audio Anal Lab, Aalborg, Denmark

[2] Aalborg Univ, Dept Elect Syst, Aalborg, Denmark

来源：

2015 23RD EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO) | 2015年

关键词：

speaker de-identification; speaker identification; speaker transformation;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Speaker de-identification is an interesting and newly investigated task in speech processing. In the current implementations, this task is based on transforming one speaker speech to another speaker in order to hide the speaker identity. In this paper we present a discriminative approach for human speaker selection for speaker de-identification. We used two modules, a speaker identification system and a speaker transformation one, to select the most appropriate speaker to transform the source speaker speech from a set of speakers, In order to select the target speaker, we minimize the identification confidence of the transformed speech as the source speaker and maximize the confusion about the transformed speech membership to the rest of the speaker models and the identification confidence of the re-transformed speech using the source speaker model. These three factors are combined to achieve overall optimization performance in order to select the best target speaker to transform the source,

引用

页码：2102 / 2106

页数：5

共 50 条

[21] An Approach to Speaker Identification
Hollien, Harry
JOURNAL OF FORENSIC SCIENCES, 2016, 61 (02) : 334 - 344
[22] Discriminative feature extraction applied to speaker identification
Nealand, JH
Bradley, AB
Lech, M
2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 484 - 487
[23] Speaker Identification based on Discriminative Vector Quantization
Zhou, GY
Mikhael, WB
Proceedings of the 46th IEEE International Midwest Symposium on Circuits & Systems, Vols 1-3, 2003, : 617 - 620
[24] Learning Discriminative Features for Speaker Identification and Verification
Yadav, Sarthak
Rai, Atul
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 2237 - 2241
[25] Speaker identification using orthogonal and discriminative features
Davarpanah, SH
Mirzaei, A
Ziaei, A
IWSSIP 2005: Proceedings of the 12th International Worshop on Systems, Signals & Image Processing, 2005, : 293 - 296
[26] DISCRIMINATIVE TENSOR DICTIONARIES AND SPARSITY FOR SPEAKER IDENTIFICATION
Zubair, S.
Wang, W.
Chambers, J. A.
2014 4TH JOINT WORKSHOP ON HANDS-FREE SPEECH COMMUNICATION AND MICROPHONE ARRAYS (HSCMA), 2014, : 37 - 41
[27] A Non-intrusive and Adaptive Speaker De-Identification Scheme Using Adversarial Examples
Chen, Meng
Lu, Li
Yu, Jiadi
Chen, Yingying
Ba, Zhongjie
Lin, Feng
Ren, Kui
PROCEEDINGS OF THE 2022 THE 28TH ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING, ACM MOBICOM 2022, 2022, : 853 - 855
[28] Improving speaker de-identification with functional data analysis of f0 trajectories
Tavi, Lauri
Kinnunen, Tomi
Hautamaki, Rosa Gonzalez
SPEECH COMMUNICATION, 2022, 140 : 1 - 10
[29] Speaker identification using discriminative centroids weighting - A growing cell structure approach
Sabac, B
Gavat, I
TEXT, SPEECH AND DIALOGUE, 1999, 1692 : 171 - 174
[30] SPARSITY BASED ROBUST SPEAKER IDENTIFICATION USING A DISCRIMINATIVE DICTIONARY LEARNING APPROACH
Tzagkarakis, Christos
Mouchtaris, Athanasios
2013 PROCEEDINGS OF THE 21ST EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2013,

← 1 2 3 4 5 →