A COMPLETE END-TO-END SPEAKER VERIFICATION SYSTEM USING DEEP NEURAL NETWORKS: FROM RAW SIGNALS TO VERIFICATION RESULT

被引：0
|
作者：
Jung, Jee-Weon [1 ]
Heo, Hee-Soo [1 ]
Yang, Il-Ho [1 ]
Shim, Hye-Jin [1 ]
Yu, Ha-Jin [1 ]
机构：
[1] Univ Seoul, Sch Comp Sci, Seoul, South Korea
来源：
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2018年
关键词：
speaker verification; end-to-end system; raw audio signal;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
End-to-end systems using deep neural networks have been widely studied in the field of speaker verification. Raw audio signal processing has also been widely studied in the fields of automatic music tagging and speech recognition. However, as far as we know, end-to-end systems using raw audio signals have not been explored in speaker verification. In this paper, a complete end-to-end speaker verification system is proposed, which inputs raw audio signals and outputs the verification results. A pre-processing layer and the embedded speaker feature extraction models were mainly investigated. The proposed pre-emphasis layer was combined with a strided convolution layer for pre-processing at the first two hidden layers. In addition, speaker feature extraction models using convolutional layer and long short-term memory are proposed to be embedded in the proposed end-to-end system.
引用
收藏
页码：5349 / 5353
页数：5
相关论文
共 50 条
  • [11] End-to-End Text-Dependent Speaker Verification
    Heigold, Georg
    Moreno, Ignacio
    Bengio, Samy
    Shazeer, Noam
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5115 - 5119
  • [12] Angular Softmax Loss for End-to-end Speaker Verification
    Li, Yutian
    Gao, Feng
    Ou, Zhijian
    Sun, Jiasong
    2018 11TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2018, : 190 - 194
  • [13] Strategies for End-to-End Text-Independent Speaker Verification
    Lin, Weiwei
    Mak, Man-Wai
    Chien, Jen-Tzung
    INTERSPEECH 2020, 2020, : 4308 - 4312
  • [14] End-to-end framework for spoof-aware speaker verification
    Kang, Woo Hyun
    Alam, Jahangir
    Fathan, Abderrahim
    INTERSPEECH 2022, 2022, : 4362 - 4366
  • [15] End-to-End Residual CNN with L-GM Loss Speaker Verification System
    Shi, Xuan
    Du, Xingjian
    Zhu, Mengyao
    2018 IEEE 23RD INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP), 2018,
  • [16] ADAPTING END-TO-END NEURAL SPEAKER VERIFICATION TO NEW LANGUAGES AND RECORDING CONDITIONS WITH ADVERSARIAL TRAINING
    Bhattacharya, Gautam
    Alam, Jahangir
    Kenny, Patrick
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6041 - 6045
  • [17] End-to-end text-dependent speaker verification using novel distance measures
    Dey, Subhadeep
    Madikeri, Srikanth
    Motlicek, Petr
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3598 - 3602
  • [18] END-TO-END ATTENTION BASED TEXT-DEPENDENT SPEAKER VERIFICATION
    Zhang, Shi-Xiong
    Chen, Zhuo
    Zhao, Yong
    Li, Jinyu
    Gong, Yifan
    2016 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2016), 2016, : 171 - 178
  • [19] End-to-End Feature Learning for Text-Independent Speaker Verification
    Chen, Fangzhou
    Bian, Tengyue
    Xu, Li
    PROCEEDINGS OF THE 2019 31ST CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2019), 2019, : 3949 - 3954
  • [20] Improving Aggregation and Loss Function for Better Embedding Learning in End-to-End Speaker Verification System
    Gao, Zhifu
    Song, Yan
    McLoughlin, Ian
    Li, Pengcheng
    Jiang, Yiheng
    Dai, Lirong
    INTERSPEECH 2019, 2019, : 361 - 365
12345