SYNTHETIC SPEECH DETECTION WITH WAV2VEC 2.0 IN VARIOUS LANGUAGE SETTINGS

被引：0

作者：

Dropulic, Branimir ^{[1
]}

Suflaj, Miljenko ^{[1
]}

Jertec, Andrej ^{[1
]}

Obad, Leo ^{[1
]}

机构：

[1] RealNetworks KONTXT, Seattle, WA 98104 USA

来源：

2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024 | 2024年

关键词：

Synthetic speech detection; text-to-speech; wav2vec; 2.0; spoofing attack; multilingualism;

D O I：

10.1109/ICASSPW62465.2024.10627750

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Synthetic speech detection plays an important role in fending off ever-increasing malicious use of voice deepfake technologies. However, its robustness and generalization have not yet been explored in diverse language settings. In this paper, we primarily analyze how such a system is affected by: (i) biases caused by different textual domains within human and synthetic samples, (ii) unseen languages, and (iii) non-native speech. Two human speech datasets, FLEURS and ARCTIC (CMU and L2), were extended with generated text-to-speech (TTS) samples. The results indicate that the wav2vec 2.0 based models are agnostic to the aforementioned points.

引用

页码：585 / 589

页数：5

共 50 条

[41] Audio Features from the Wav2Vec 2.0 Embeddings for the ACM Multimedia 2022 Stuttering Challenge
Montacie, Claude
Caraty, Marie-Jose
Lackovic, Nikola
PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 7195 - 7199
[42] Exploring the potential of Wav2vec 2.0 for speech emotion recognition using classifier combination and attention-based feature fusion
Nasersharif, Babak
Namvarpour, Mohammad
JOURNAL OF SUPERCOMPUTING, 2024, 80 (16): : 23667 - 23688
[43] Applying the conformal prediction paradigm for the uncertainty quantification of an end-to-end automatic speech recognition model (wav2vec 2.0)
Ernez, Fares
Arnold, Alexandre
Galametz, Audrey
Kobus, Catherine
Ould-Amer, Nawal
CONFORMAL AND PROBABILISTIC PREDICTION WITH APPLICATIONS, VOL 204, 2023, 204 : 16 - 35
[44] Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model
Vyas, Apoorv
Madikeri, Srikanth
Bourlard, Herve
INTERSPEECH 2021, 2021, : 2861 - 2865
[45] Low Resource Comparison of Attention-based and Hybrid ASR Exploiting wav2vec 2.0
Rouhe, Aku
Virkkunen, Anja
Leinonen, Juho
Kurimo, Mikko
INTERSPEECH 2022, 2022, : 3543 - 3547
[46] CTRL: Continual Representation Learning to Transfer Information of Pre-trained for WAV2VEC 2.0
Lee, Jae-Hong
Lee, Chae-Won
Choi, Jin-Seong
Chang, Joon-Hyuk
Seong, Woo Kyeong
Lee, Jeonghan
INTERSPEECH 2022, 2022, : 3398 - 3402
[47] Keyword spotting for dialectal speech and Introduction of wav2vec2.0
Ariga, Tomohiro
Minakawa, Reo
Kojima, Kazunori
Lee, Shi-Wook
Itoh, Yoshiaki
APSIPA ASC 2024 - Asia Pacific Signal and Information Processing Association Annual Summit and Conference 2024, 2024,
[48] Analyzing Wav2Vec 1.0 Embeddings for Cross-Database Parkinson's Disease Detection and Speech Features Extraction
Klempir, Ondrej
Krupicka, Radim
SENSORS, 2024, 24 (17)
[49] Improving Tone Recognition Performance using Wav2vec 2.0-Based Learned Representation in Yoruba, a Low-Resourced Language
Obiang, Saint germes b. bengono
Tsopze, Norbert
Yonta, Paulin melatagia
Bonastre, Jean-francois
Jimenez, Tania
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2024, 23 (12)
[50] Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Hsu, Wei-Ning
Sriram, Anuroop
Baevski, Alexei
Likhomanenko, Tatiana
Xu, Qiantong
Pratap, Vineel
Kahn, Jacob
Lee, Ann
Collobert, Ronan
Synnaeve, Gabriel
Auli, Michael
INTERSPEECH 2021, 2021, : 721 - 725

← 1 2 3 4 5 →