mlsanityData to 14 Oct 2026

Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing

arXiv 2409.08346 ↗First posted 12 Sep 2024eess.AS cs.AI cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are mainly in English, and the high cost of acquiring multilingual datasets hinders training language-independent models. We initiate this work by evaluating top-performing speech anti-spoofing systems that are trained on English data but tested on other languages, observing notable performance declines. We propose an innovative approach - Accent-based data expansion via TTS (ACCENT), which introduces diverse linguistic knowledge to monolingual-trained models, improving their cross-lingual capabilities. We conduct experiments on a large-scale dataset consisting of over 3 million samples, including 1.8 million training samples and nearly 1.2 million testing samples across 12 languages. The language mismatch effects are preliminarily quantified and remarkably reduced over 15% by applying the proposed ACCENT. This easily implementable method shows promise for multilingual and low-resource language scenarios.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 12 Sep 2024.

Builds on

35 of 45 references.

References · 35

  1. 2017Squeeze-and-Excitation Networkscited by 4,789
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  3. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  4. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 501
  5. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  6. 2018Efficient Neural Audio Synthesiscited by 219
  7. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  8. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  9. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 178
  10. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  11. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 117
  12. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
23 more
  1. 2019Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloningcited by 66
  2. 2019CSS10: A Collection of Single Speaker Speech Datasets for 10 Languagescited by 54
  3. 2022The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterancecited by 47
  4. 2023An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verificationcited by 42
  5. 2020Replay and Synthetic Speech Detection with Res2net Architecturecited by 39
  6. 2020One Model, Many Languages: Meta-learning for Multilingual Text-to-Speechcited by 28
  7. 2023SingFake: Singing Voice Deepfake Detectioncited by 21
  8. 2022Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoderscited by 20
  9. 2021Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attackscited by 18
  10. 2024ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiencycited by 18
  11. 2024Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detectioncited by 17
  12. 2021Human Perception of Audio Deepfakescited by 15
  13. 2023Disentangling Voice and Content with Self-Supervision for Speaker Recognitioncited by 13
  14. 2022MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterancescited by 12
  15. 2023FSD: An Initial Chinese Dataset for Fake Song Detectioncited by 12
  16. 2023Improving Short Utterance Anti-Spoofing with AASIST2cited by 11
  17. 2024How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?cited by 10
  18. 2023Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verificationcited by 8
  19. 2024Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024cited by 7
  20. 2017Cross-lingual Speaker Verification with Deep Feature Learningcited by 6
  21. 2024Neural Codec-based Adversarial Sample Detection for Speaker Verificationcited by 5
  22. 2024Analyzing the Impact of Splicing Artifacts in Partially Fake Speech Signalscited by 4
  23. 2024SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plancited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingcited by 19
  2. 2025Multilingual Source Tracing of Speech Deepfakes: A First Benchmarkcited by 7
  3. 2026EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesiscited by 3
  4. 2025Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detectioncited by 2
  5. 2025Interpolating Speaker Identities in Embedding Space for Data Expansioncited by 1
  6. 2025QAMO: Quality-aware Multi-centroid One-class Learning For Speech Deepfake Detectioncited by 1
  7. 2026Supervised Post-training of Speech Foundation Models for Robust Adaptation in Speech Deepfake Detectioncited by 0