ASVtorch toolkit: Speaker verification with deep neural networks

被引：4
|
作者：
Lee, Kong Aik [1 ]
Vestman, Ville [2 ]
Kinnunen, Tomi [2 ]
机构：
[1] ASTAR, Inst Infocomm Res, Singapore, Singapore
[2] Univ Eastern Finland, Computat Speech Grp, Joensuu, Finland
来源：
SOFTWAREX | 2021年 / 14卷
基金：
芬兰科学院;
关键词：
Speaker recognition; PyTorch; Deep learning; RECOGNITION;
D O I：
10.1016/j.softx.2021.100697
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
The human voice differs substantially between individuals. This facilitates automatic speaker verification (ASV) - recognizing a person from his/her voice. ASV accuracy has substantially increased throughout the past decade due to recent advances in machine learning, particularly deep learning methods. An unfortunate downside has been substantially increased complexity of ASV systems. To help non experts to kick-start reproducible ASV development, a state-of-the-art toolkit implementing various ASV pipelines and functionalities is required. To this end, we introduce a new open-source toolkit, ASVtorch, implemented in Python using the widely used PyTorch machine learning framework. (C) 2021 The Author(s). Published by Elsevier B.V.
引用
收藏
页数：6
相关论文
共 50 条
  • [1] STUDY ON THE TEMPORAL POOLING USED IN DEEP NEURAL NETWORKS FOR SPEAKER VERIFICATION
    Rouvier, Mickael
    Bousquet, Pierre-Michel
    Duret, Jarod
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 501 - 505
  • [2] DEEP NEURAL NETWORKS FOR SMALL FOOTPRINT TEXT-DEPENDENT SPEAKER VERIFICATION
    Variani, Ehsan
    Lei, Xin
    McDermott, Erik
    Moreno, Ignacio Lopez
    Gonzalez-Dominguez, Javier
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [3] SNR-Invariant Multitask Deep Neural Networks for Robust Speaker Verification
    Yao, Qi
    Mak, Man-Wai
    IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (11) : 1670 - 1674
  • [4] Insights into Deep Neural Networks for Speaker Recognition
    Garcia-Romero, Daniel
    McCree, Alan
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 1141 - 1145
  • [5] Deep Speaker Embeddings for Short-Duration Speaker Verification
    Bhattacharya, Gautam
    Alam, Jahangir
    Kenny, Patrick
    18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 1517 - 1521
  • [6] Deep speaker embeddings for Speaker Verification: Review and experimental comparison
    Jakubec, Maros
    Jarina, Roman
    Lieskovska, Eva
    Kasak, Peter
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 127
  • [7] Regularized Auto-Associative Neural Networks for Speaker Verification
    Sri Garimella
    Mallidi, Harish
    Hermansky, Hynek
    IEEE SIGNAL PROCESSING LETTERS, 2012, 19 (12) : 841 - 844
  • [8] Multi-task learning of deep neural networks for joint automatic speaker verification and spoofing detection
    Li, Jiakang
    Sun, Meng
    Zhang, Xiongwei
    2019 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2019, : 1517 - 1522
  • [9] A deep learning approach to integrate convolutional neural networks in speaker recognition
    Hourri, Soufiane
    Nikolov, Nikola S.
    Kharroubi, Jamal
    INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2020, 23 (03) : 615 - 623
  • [10] A deep learning approach to integrate convolutional neural networks in speaker recognition
    Soufiane Hourri
    Nikola S. Nikolov
    Jamal Kharroubi
    International Journal of Speech Technology, 2020, 23 : 615 - 623
12345