ATTENTION-BASED MODELS FOR TEXT-DEPENDENT SPEAKER VERIFICATION

被引：0

作者：

Chowdhury, F. A. Rezaur Rahman ^{[1
]}

Wang, Quan ^{[2
]}

Moreno, Ignacio Lopez ^{[2
]}

Wan, Li ^{[2
]}

机构：

[1] Washington State Univ, Pullman, WA 99164 USA

[2] Google Inc, Mountain View, CA USA

来源：

2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2018年

关键词：

Attention-based model; sequence summarization; speaker recognition; pooling; LSTM;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence. In this paper, we analyze the usage of attention mechanisms to the problem of sequence summarization in our end-to-end text-dependent speaker recognition system. We explore different topologies and their variants of the attention layer. and compare different pooling methods on the attention weights. Ultimately, we show that attention-based models can improves the Equal Error Rate (EER) of our speaker verification system by relatively 14% compared to our non-attention LSTM baseline model.

引用

页码：5359 / 5363

页数：5

共 50 条

[41] Addressing Text-Dependent Speaker Verification Using Singing Speech
Shi, Yan
Zhou, Juanjuan
Long, Yanhua
Li, Yijie
Mao, Hongwei
[J]. APPLIED SCIENCES-BASEL, 2019, 9 (13):
[42] Unsupervised Learning of HMM Topology for Text-dependent Speaker Verification
Liu, Ming
Huang, Thomas
[J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 921 - 924
[43] EXPLORING SEQUENTIAL CHARACTERISTICS IN SPEAKER BOTTLENECK FEATURE FOR TEXT-DEPENDENT SPEAKER VERIFICATION
Chen, Liping
Zhao, Yong
Zhang, Shi-Xiong
Li, Jie
Ye, Guoli
Soong, Frank
[J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5364 - 5368
[44] Multi-Task Learning for Text-dependent Speaker Verification
Chen, Nanxin
Qian, Yanmin
Yu, Kai
[J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 185 - 189
[45] EFFECTS OF GENDER INFORMATION IN TEXT-INDEPENDENT AND TEXT-DEPENDENT SPEAKER VERIFICATION
Kanervisto, Anssi
Vestman, Ville
Sahidullah, Md
Hautamaki, Ville
Kinnunen, Tomi
[J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5360 - 5364
[46] Weighting scores to improve speaker-dependent threshold estimation in text-dependent speaker verification
Saeta, JR
Hernando, J
[J]. NONLINEAR ANALYSES AND ALGORITHMS FOR SPEECH PROCESSING, 2005, 3817 : 81 - 91
[47] Improving X-vector and PLDA for Text-dependent Speaker Verification
Chen, Zhuxin
Lin, Yue
[J]. INTERSPEECH 2020, 2020, : 726 - 730
[48] Text-dependent speaker verification: Classifiers, databases and RSR2015
Larcher, Anthony
Lee, Kong Aik
Ma, Bin
Li, Haizhou
[J]. SPEECH COMMUNICATION, 2014, 60 : 56 - 77
[49] Parameterization of the score threshold for a text-dependent adaptive speaker verification system
Mirghafori, N
Hébert, M
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 361 - 364
[50] DEEP NEURAL NETWORKS FOR SMALL FOOTPRINT TEXT-DEPENDENT SPEAKER VERIFICATION
Variani, Ehsan
Lei, Xin
McDermott, Erik
Moreno, Ignacio Lopez
Gonzalez-Dominguez, Javier
[J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,

← 1 2 3 4 5 →