Suchergebnisse - "Automatic speaker verification"

Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymization

Autoren: Tomashenko, Natalia Vincent, Emmanuel Tommasi, Marc

Weitere Verfasser: Tomashenko, Natalia Vincent, Emmanuel Tommasi, Marc

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-5

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Computer Science - Computation and Language, Speech temporal dynamics, [INFO] Computer Science [cs], Computer Science - Sound, anonymization, Audio and Speech Processing (eess.AS), speech rate, FOS: Electrical engineering, electronic engineering, information engineering, phoneme duration characteristics, Computation and Language (cs.CL), automatic speaker verification, Electrical Engineering and Systems Science - Audio and Speech Processing

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2412.17164
https://hal.science/hal-04853872v1
https://hal.science/hal-04853872v1/document
https://doi.org/10.1109/icassp49660.2025.10887896

SpoofCeleb: Speech Deepfake Detection and SASV in the Wild

Autoren: Jee-weon Jung Yihan Wu Xin Wang et al.

Quelle: IEEE Open Journal of Signal Processing, Vol 6, Pp 68-77 (2025)

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), speech deepfake detection, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Audio and Speech Processing (eess.AS), In the wild, spoofing-robust automatic speaker verification, FOS: Electrical engineering, electronic engineering, information engineering, Electrical engineering. Electronics. Nuclear engineering, Computer Science - Sound, TK1-9971, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/abs/2409.17285
https://doaj.org/article/8c6a60682d1c4eb89c30a4554f5fe199

DeepLASD countermeasure for logical access audio spoofing

Autoren: Hamed Al-Tairi Ali Javed Tasawer Khan et al.

Quelle: Scientific Reports, Vol 15, Iss 1, Pp 1-10 (2025)

Schlagwörter: Automatic speaker verification, Deep learning, Logical access attacks, Spoof detection, Text-to-speech synthesis, Voice conversion, Medicine, Science

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/2045-2322

Zugangs-URL: https://doaj.org/article/a172e9dc5ce24e4cb616b8d446964545

The First VoicePrivacy Attacker Challenge

Autoren: Tomashenko, Natalia Miao, Xiaoxiao Vincent, Emmanuel et al.

Weitere Verfasser: Tomashenko, Natalia Miao, Xiaoxiao Vincent, Emmanuel et al.

Quelle: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). :1-2

Schlagwörter: FOS: Computer and information sciences, Computer Science - Computation and Language, Computer Science - Cryptography and Security, [INFO] Computer Science [cs], Voice privacy voice anonymization attacker system automatic speaker verification, voice anonymization, Audio and Speech Processing (eess.AS), Voice privacy, FOS: Electrical engineering, electronic engineering, information engineering, Computation and Language (cs.CL), Cryptography and Security (cs.CR), automatic speaker verification, attacker system, Electrical Engineering and Systems Science - Audio and Speech Processing

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2504.14183
https://hal.science/hal-05040330v1/document
https://doi.org/10.1109/icassp49660.2025.10888513
https://hal.science/hal-05040330v1

Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems

Autoren: Tomashenko, Natalia Vincent, Emmanuel Tommasi, Marc

Weitere Verfasser: Tomashenko, Natalia Vincent, Emmanuel Tommasi, Marc

Schlagwörter: FOS: Computer and information sciences, Sound (cs.SD), Cryptography and Security, [INFO] Computer Science [cs], attack model, anonymization, context-dependent duration features, Sound, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computation and Language, Computation and Language (cs.CL), Cryptography and Security (cs.CR), Audio and Speech Processing, automatic speaker verification

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2507.15214
https://hal.science/hal-05099074v1

t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators

Autoren: Tomi H. Kinnunen Kong Aik Lee Hemlata Tak et al.

Quelle: IEEE Transactions on Pattern Analysis and Machine Intelligence. 46:2622-2637

Schlagwörter: FOS: Computer and information sciences, biometrics, Computer Science - Machine Learning, Sound (cs.SD), Computer Science - Cryptography and Security, tandem evaluation, Image and Video Processing (eess.IV), Electrical Engineering and Systems Science - Image and Video Processing, Statistics - Computation, Computer Science - Sound, Machine Learning (cs.LG), presentation attack detection, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, equal error rate, Cryptography and Security (cs.CR), Computation (stat.CO), automatic speaker verification, Electrical Engineering and Systems Science - Audio and Speech Processing

Dateibeschreibung: application/pdf

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/37695972
http://arxiv.org/abs/2309.12237
https://erepo.uef.fi/handle/123456789/34048

Voice spoofing countermeasure for voice replay attacks using deep learning

Autoren: Zhou, Jincheng Hai, Tao Jawawi, Dayang N. A. et al.

Quelle: Journal of Cloud Computing. 11(1)

Schlagwörter: Automatic Speaker Verification (ASV), spoofing, voice biometrics, deep learning, neural network, machine learning

Dateibeschreibung: electronic

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-40069
https://doi.org/10.1186/s13677-022-00306-5

Discriminative deep learning based hybrid spectro-temporal features for synthetic voice spoofing detection

Autoren: Pranita, Niraj Palsapure Rajeswari, Rajeswari Sandeep, Kumar Kempegowda et al.

Schlagwörter: Automatic speaker verification, Hybrid feature learning, LSTM-CNN, Spectral-temporal feature, Spoofing attack detection

Relation: https://zenodo.org/records/14890159; oai:zenodo.org:14890159

Verfügbarkeit: https://doi.org/10.11591/ijai.v14.i1.pp130-141
https://zenodo.org/records/14890159

Target Speaker Anonymization In Multi-Speaker Recordings

Autoren: Tomashenko, Natalia Yamagishi, Junichi Wang, Xin et al.

Weitere Verfasser: Tomashenko, Natalia Yamagishi, Junichi Wang, Xin et al.

Quelle: https://hal.science/hal-05308244 ; 2025.

Schlagwörter: target speaker anonymization (TSA), privacy, automatic speech recognition (ASR), automatic speaker verification (ASV), target speaker extraction (TSE), speaker diarization, [INFO]Computer Science [cs]

Verfügbarkeit: https://hal.science/hal-05308244
https://hal.science/hal-05308244v1/document
https://hal.science/hal-05308244v1/file/TSA_hal.pdf

RawSpectrogram: On the Way to Effective Streaming Speech Anti-Spoofing

Autoren: Petr Grinberg Vladislav Shikhov

Quelle: IEEE Access, Vol 11, Pp 109928-109938 (2023)

Schlagwörter: ASVspoof challenge, automatic speaker verification system, SASV challenge, Electrical engineering. Electronics. Nuclear engineering, Anti-spoofing, countermeasure, spoofing-aware speaker verification system, TK1-9971

Zugangs-URL: https://doaj.org/article/986cc4060ce34aef922488f7ed5264b3

On the Defense of Spoofing Countermeasures Against Adversarial Attacks

Autoren: Long Nguyen-Vu Thien-Phuc Doan Mai Bui et al.

Quelle: IEEE Access, Vol 11, Pp 94563-94574 (2023)

Schlagwörter: adversarial attack, Automatic speaker verification, spoofing countermeasure, psychoacoustics, Electrical engineering. Electronics. Nuclear engineering, TK1-9971

Zugangs-URL: https://doaj.org/article/5bce239f339341229ae00dece6f51ffd

Vulnerability issues in Automatic Speaker Verification (ASV) systems

Autoren: Priyanka Gupta Hemant A. Patil Rodrigo Capobianco Guido

Quelle: EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-14 (2024)

Schlagwörter: Automatic speaker verification, Spoofing attacks, Attacker’s perspective, Adversarial attacks, Deepfake, Acoustics. Sound, QC221-246, Electronic computers. Computer science, QA75.5-76.95

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/1687-4722

Zugangs-URL: https://doaj.org/article/76c6fa0cd1de49d1b8b11fb6d2a8e914

Dual-Stream Temporal Convolutional Neural Network for Voice Presentation Attack Detection

Autoren: Gonzalez-Soler, Lazaro Gomez-Barrero, Marta Kamble, Madhu et al.

Weitere Verfasser: Gonzalez-Soler, Lazaro Gomez-Barrero, Marta Kamble, Madhu et al.

Quelle: 2022 International Workshop on Biometrics and Forensics (IWBF). :1-6

Schlagwörter: Generalisation Capability, Presentation Attack Detection, Temporal Convolutional Neural Network, Automatic Speaker Verification, [INFO.INFO-IA] Computer Science [cs]/Computer Aided Engineering

Voice Liveness Detection Using Bump Wavelet with CNN

Autoren: Priyanka Gupta Siddhant Gupta Hemant A. Patil et al.

Weitere Verfasser: Priyanka Gupta Siddhant Gupta Hemant A. Patil et al.

Quelle: Lecture Notes in Computer Science ISBN: 9783031126994

Schlagwörter: [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, scalogram, Voice liveness detection, [INFO] Computer Science [cs], CNN, [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD], automatic speaker verification, pop noise, bump wavelet

Dateibeschreibung: application/pdf

Zugangs-URL: https://hal.science/hal-03690065v1

Automatic Voice Identification after Speech Resynthesis using PPG

Autoren: Gaudier, Thibault Tahon, Marie Larcher, Anthony et al.

Weitere Verfasser: Gaudier, Thibault Tahon, Marie Larcher, Anthony et al.

Quelle: Speaker and Language Recognition Workshop - Odyssey ; https://hal.science/hal-04638686 ; Speaker and Language Recognition Workshop - Odyssey, Jun 2024, Québec (Canada), Canada

Schlagwörter: Speech synthesis, speech edition, Interpretability, phonetic posteriograms, Automatic speaker verification, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing

Time: Québec (Canada), Canada

Relation: info:eu-repo/semantics/altIdentifier/arxiv/2408.02712; info:eu-repo/grantAgreement//101007666,/EU/esperanto/Exchanges for SPEech ReseArch aNd TechnOlogies; info:eu-repo/grantAgreement//957017/EU/Stream Learning for Multilingual Knowledge Transfer/SELMA; ARXIV: 2408.02712

Verfügbarkeit: https://hal.science/hal-04638686
https://hal.science/hal-04638686v1/document
https://hal.science/hal-04638686v1/file/Odyssey_PPG_Conversion.pdf

On the Invertibility of a Voice Privacy System Using Embedding Alignment

Autoren: Champion, Pierre Thebaud, Thomas Le Lan, Gaël et al.

Weitere Verfasser: Champion, Pierre Thebaud, Thomas Le Lan, Gaël et al.

Quelle: 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). :191-197

Schlagwörter: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Computer Science - Machine Learning, Sound (cs.SD), Wasserstein-Procrustes, Computer Science - Cryptography and Security, Procrustes Analysis, 02 engineering and technology, Voice Privacy, Computer Science - Sound, Machine Learning (cs.LG), 03 medical and health sciences, Audio and Speech Processing (eess.AS), 0202 electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, Automatic Speaker Verification, 0305 other medical science, Cryptography and Security (cs.CR), [INFO.INFO-CR] Computer Science [cs]/Cryptography and Security [cs.CR], Electrical Engineering and Systems Science - Audio and Speech Processing

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2110.05431
https://hal.science/hal-03356021v2/document
https://hal.science/hal-03356021v2

Privacy-Preserving Voice Anti-Spoofing Using Secure Multi-Party Computation

Autoren: Chouchane, Oubaïda Brossier, Baptiste Gamboa, Jorge Esteban Gamboa et al.

Weitere Verfasser: Chouchane, Oubaïda Brossier, Baptiste Gamboa, Jorge Esteban Gamboa et al.

Quelle: Interspeech 2021

Schlagwörter: Spoofing, 03 medical and health sciences, Privacy-preservation, Automatic speaker verification, 0202 electrical engineering, electronic engineering, information engineering, Secure multi-party computation, 02 engineering and technology, 0305 other medical science, [INFO.INFO-IA] Computer Science [cs]/Computer Aided Engineering

Adversarial Transformation of Spoofing Attacks for Voice Biometrics

Autoren: Gómez Alanís, Alejandro González López, José Andrés Peinado Herreros, Antonio Miguel

Quelle: IberSPEECH 2021. :255-259

Schlagwörter: Voice biometrics, 03 medical and health sciences, Audio and Speech Processing (eess.AS), Automatic speaker verification, Adversarial attacks, Presentation attack detection, FOS: Electrical engineering, electronic engineering, information engineering, 0305 other medical science, Electrical Engineering and Systems Science - Audio and Speech Processing

Zugangs-URL: http://arxiv.org/pdf/2201.01226
http://arxiv.org/abs/2201.01226
https://dblp.uni-trier.de/db/conf/iberspeech/iberspeech2021.html#Alanis0P21
https://hdl.handle.net/10481/80775

スペクトル変調・時間変調分析に基づく音響信号の高度な特徴表現とその応用

Autoren: 李, 凱

Schlagwörter: Spectral temporal modulation, Human auditory perception, Fake audio detection, Automatic speaker verification, Machine anomalous sounds detection

Dateibeschreibung: application/pdf

Zugangs-URL: https://ndlsearch.ndl.go.jp/books/R100000039-I13724647

Degree: 博士(情報科学) -- 北陸先端科学技術大学院大学

Uncertainty assessment for detection of spoofing attacks to speaker verification systems using a Bayesian approach

Autoren: Çağıl Süslü Eray Eren Cenk Demiroğlu et al.

Weitere Verfasser: Çağıl Süslü Eray Eren Cenk Demiroğlu et al.

Quelle: Speech Communication. 137:44-51

Schlagwörter: 03 medical and health sciences, Automatic speaker verification, 0103 physical sciences, Uncertainty, Speech, Spoofing countermeasure system, 0305 other medical science, Bayesian, 01 natural sciences

Zugangs-URL: http://hdl.handle.net/10679/8548
https://doi.org/10.1016/j.specom.2021.12.003