☆ 4.6 Article

End-to-End Dual-Branch Network Towards Synthetic Speech Detection

IEEE SIGNAL PROCESSING LETTERS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Electrical & Electronic

Synthetic Speech Detection Based on Local Autoregression and Variance Statistics

Sanshuai Cui et al.

Summary: With the development of speech synthesis technology, the paper proposes novel speech features called ARS based on AR modeling and standard deviation statistics, and a new back-end classifier called scDenseNet. Experimental results show that ARS has strong representation and sensitivity to spoofing attacks, and scDenseNet outperforms previous classifiers and achieves the best performance compared to other state-of-the-art classifiers.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

The Role of Long-Term Dependency in Synthetic Speech Detection

Changtao Li et al.

Summary: Researchers propose a back-end classifier for synthetic speech detection based on Transformer Encoder, which utilizes one-dimensional convolution and supervised contrastive loss to capture long-term dependencies and achieves better performance with fewer parameters.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Proceedings Paper Audiology & Speech-Language Pathology

A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection

Xin Wang et al.

Summary: Recent research has focused on back-end neural networks and training criteria for speech spoofing countermeasures. This study offers a comparative perspective on various models and recognizes the potential impact of random initial seed on model performance. Promising techniques, including average pooling and a new hyper-parameter-free loss function, led to the best single model with significantly different statistical performance compared to others.

INTERSPEECH 2021 (2021)

添加到收藏夹

Proceedings Paper Audiology & Speech-Language Pathology

An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems

You Zhang et al.

Summary: Spoofing countermeasure systems are crucial in speaker verification, aiming to distinguish between spoofing attacks and authentic speech trials. The study found significant performance degradation in cross-dataset experiments compared to single-dataset performance, hypothesizing channel mismatch as a key reason. Several channel robust strategies were proposed and demonstrated to significantly improve the performance of CM systems in such scenarios.

INTERSPEECH 2021 (2021)

添加到收藏夹

Proceedings Paper Audiology & Speech-Language Pathology

Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks

Xu Li et al.

Summary: The study introduces a novel channel-wise gated Res2Net (CG-Res2Net) approach, modifying Res2Net to enable a channel-wise gating mechanism in the connection between feature groups, thereby enhancing the detection generalizability of the system.

INTERSPEECH 2021 (2021)

添加到收藏夹

Article Acoustics

Modified Magnitude-Phase Spectrum Information for Spoofing Detection

Jichen Yang et al.

Summary: The study introduces a novel feature representation method MMPS and CQMOC for spoofing detection, outperforming traditional handcrafted feature representations. These new features perform well across various anti-spoofing models, with the designed TCMS and MTL methods showing promising results in unknown-kind spoofing detection.

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING (2021)

添加到收藏夹

Proceedings Paper Acoustics

REPLAY AND SYNTHETIC SPEECH DETECTION WITH RES2NET ARCHITECTURE

Xu Li et al.

Summary: By introducing the Res2Net model structure and multi-scale mechanism, the generalizability of the anti-spoofing countermeasure has been improved, and the model size has been reduced. Experimental results show that the performance of Res2Net in the ASVspoof 2019 corpus is significantly better than other models, especially excelling in physical access and logical access scenarios.

2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) (2021)

添加到收藏夹

Proceedings Paper Acoustics

A CAPSULE NETWORK BASED APPROACH FOR DETECTION OF AUDIO SPOOFING ATTACKS

Anwei Luo et al.

Summary: The study introduced a capsule network to enhance the generalization of audio anti-spoofing systems, to detect fake audios synthesized by advanced methods and combat various attacks, including text-to-speech and voice conversion attacks. The results demonstrated that this approach is also highly capable of detecting replay attacks.

2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

ResMax: Detecting Voice Spoofing Attacks with Residual Network and Max Feature Map

Il-Youp Kwak et al.

Summary: The 2019 ASVspoof competition aimed to design highly accurate voice spoofing attack detection systems, with top solutions using ensemble methods combining multiple deep learning models. Researchers combined skip connections and max feature maps, optimized CQT features, and achieved better results on the evaluation set.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Towards End-to-End Synthetic Speech Detection

Guang Hua et al.

Summary: This paper introduces a new synthetic speech detection approach, the TSSDNet model, which utilizes end-to-end DNN and eliminates the need for hand-crafted feature extraction. Experimental results show significant performance improvement, demonstrating the potential and advantages of this model in synthetic speech detection.

IEEE SIGNAL PROCESSING LETTERS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

One-Class Learning Towards Synthetic Voice Spoofing Detection

You Zhang et al.

Summary: This study introduces an anti-spoofing system using one-class learning to detect unknown synthetic voice spoofing attacks, achieving excellent results without relying on data augmentation methods.

IEEE SIGNAL PROCESSING LETTERS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Generalized end -to -end detection of spoofing attacks to automatic speaker recognizers

Joao Monteiro et al.

COMPUTER SPEECH AND LANGUAGE (2020)

添加到收藏夹

Proceedings Paper Acoustics

ADVERSARIAL MULTI-TASK LEARNING FOR SPEAKER NORMALIZATION IN REPLAY DETECTION

Gajan Suthokumar et al.

2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (2020)

添加到收藏夹

Article Acoustics

Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals

Tomi Kinnunen et al.

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING (2020)

添加到收藏夹

Article Computer Science, Theory & Methods

Significance of Subband Features for Synthetic Speech Detection

Jichen Yang et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2020)

添加到收藏夹

Article Acoustics

Extraction of Octave Spectra Information for Spoofing Attack Detection

Jichen Yang et al.

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Synthetic speech detection using fundamental frequency variation and spectral features

Monisankha Pal et al.

COMPUTER SPEECH AND LANGUAGE (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Constant Q cepstral coefficients: A spoofing countermeasure for automatic speaker verification

Massimiliano Todisco et al.

COMPUTER SPEECH AND LANGUAGE (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection

Tomi Kinnunen et al.

18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION (2017)

添加到收藏夹

Article Computer Science, Theory & Methods

Toward a Universal Synthetic Speech Spoofing Detection Using Phase Information

Jon Sanchez et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2015)

添加到收藏夹

Article Acoustics

Spoofing and countermeasures for speaker verification: A survey

Zhizheng Wu et al.

SPEECH COMMUNICATION (2015)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.