STACKED BOTTLENECK FEATURES FOR SPEAKER VERIFICATION

被引：0

作者：

Tian, Yao ^{[1
]}

He, Liang ^{[1
]}

Liu, Jia ^{[1
]}

机构：

[1] Tsinghua Univ, Natl Lab Informat Sci & Technol, Dept Elect Engn, Beijing 100084, Peoples R China

来源：

2015 IEEE CHINA SUMMIT & INTERNATIONAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING | 2015年

关键词：

speaker verification; GMM supervector; deep neural network; bottleneck feature;

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：

i-vector modeling has shown to be effective for text independent speaker verification. It represents each utterance as a low-dimensional vector using factor analysis with a GMM supervector. In order to capture more complex speaker statistics, this paper proposes a new feature representation other than i-vectors for speaker verification using neural networks. In this work, stacked bottleneck features are extracted from cascade neural networks based on GMM supervectors. Dropout is integrated into the model to improve generalization error. We compare the proposed method with i-vector approach on NIST SRE2008 female short2-short3 telephone-telephone task. Experimental results demonstrate the efficacy of the proposed method.

引用

页码：514 / 518

页数：5

共 50 条

[1] Adversarial Network Bottleneck Features for Noise Robust Speaker Verification
Yu, Hong
Tan, Zheng-Hua
Ma, Zhanyu
Guo, Jun
[J]. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 1492 - 1496
[2] Investigating the stacked phonetic bottleneck feature for speaker verification with short voice commands
Huang, Yichi
Zou, Yuexian
Liu, Yi
[J]. PROCEEDINGS 2017 4TH IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR), 2017, : 706 - 711
[3] Investigation of Bottleneck Features and Multilingual Deep Neural Networks for Speaker Verification
Tian, Yao
Cai, Meng
He, Liang
Liu, Jia
[J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 1151 - 1155
[4] Latent Factor Analysis of Deep Bottleneck Features for Speaker Verification with Random Digit Strings
Shi, Ziqiang
Lin, Huibin
Liu, Liu
Liu, Rujie
[J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1081 - 1085
[5] DNN bottleneck features for speaker clustering
Jorrin, Jesus
Garcia, Paola
Buera, Luis
[J]. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 1024 - 1028
[6] Fusion of bottleneck, spectral and modulation spectral features for improved speaker verification of neutral and whispered speech
Sarria-Paja, Milton
Falk, Tiago H.
[J]. SPEECH COMMUNICATION, 2018, 102 : 78 - 86
[7] Multi-Task Adversarial Network Bottleneck Features for Noise-Robust Speaker Verification
Yu, Hong
Hu, Tianrui
Ma, Zhanyu
Tan, Zheng-Hua
Guo, Jun
[J]. PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON NETWORK INFRASTRUCTURE AND DIGITAL CONTENT (IEEE IC-NIDC), 2018, : 165 - 169
[8] DEEP BOTTLENECK FEATURES FOR I-VECTOR BASED TEXT-INDEPENDENT SPEAKER VERIFICATION
Ghalehjegh, Sina Hamidi
Rose, Richard C.
[J]. 2015 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2015, : 555 - 560
[9] Speaker Verification with Deep Features
Liu, Yuan
Fu, Tianfan
Fan, Yuchen
Qian, Yanmin
Yu, Kai
[J]. PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 747 - 753
[10] Prosodic Features for Speaker Verification
Mary, Leena
Yegnanarayana, B.
[J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 917 - 920

← 1 2 3 4 5 →