mlsanityData to 19 Oct 2026

Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features

arXiv 2309.16954 ↗First posted 29 Sep 2023eess.AS cs.SDcited by 1

On the map: Speech and audio language models → Vocoders and speech synthesis

Abstract (arXiv)

Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this paper, the flaws of the speaker features inherent in the text-to-speech (TTS) process are analyzed. Differences in the temporal consistency of intra-utterance speaker features arise due to the lack of fine-grained control over speaker features in TTS. Since the speaker representations in TTS are based on speaker embeddings extracted by encoders, the distribution of inter-utterance speaker features differs between synthetic and bonafide speech. Based on these analyzes, an SSD method based on temporal consistency and distribution of speaker features is proposed. On one hand, modeling the temporal consistency of intra-utterance speaker features can aid speech anti-spoofing. On the other hand, distribution differences in inter-utterance speaker features can be utilized for SSD. The proposed method offers low computational complexity and performs well in both cross-dataset and silence trimming scenarios.

Key facts. Cited by 1 paper in the map (data through 19 Oct 2026). Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models. Builds on 23 of its 48 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

23 of 48 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021A Survey on Neural Speech Synthesis29 Jun

Other references · 22

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 4,385
  2. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 238
  3. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 235
  4. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 210
  5. 2020End-to-end anti-spoofing with RawNet2cited by 196
  6. 2022Does Audio Deepfake Detection Generalize?cited by 166
  7. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 96
  8. 2019STC Antispoofing Systems for the ASVspoof2019 Challengecited by 72
  9. 2021A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detectioncited by 71
  10. 2020Replay and Synthetic Speech Detection with Res2net Architecturecited by 47
  11. 2021Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?cited by 46
  12. 2019ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworkscited by 33
10 more
  1. 2022Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoderscited by 33
  2. 2022SASV 2022: The First Spoofing-Aware Speaker Verification Challengecited by 31
  3. 2022Deepfake audio detection by speaker verificationcited by 16
  4. 2022The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challengecited by 11
  5. 2022Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker Verification Systemscited by 8
  6. 2022Optimizing Tandem Speaker Verification and Anti-Spoofing Systemscited by 7
  7. 2022SASV Based on Pre-trained ASV System and Integrated Scoring Modulecited by 3
  8. 2020Multi-task Learning Based Spoofing-Robust Automatic Speaker Verification Systemcited by 2
  9. 2021Estimating the confidence of speech spoofing countermeasurecited by 1
  10. 2022Invertible Voice Conversioncited by 1

Built on by

Cited by year (2026 to 19 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Leveraging Gradient Reversal Loss and Multitask Learning for Datasets-Aware Audio Deepfake Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection
  2. 2022Evaluating and reducing the distance between synthetic and real speech distributions
  3. 2026A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech
  4. 2025ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts
  5. 2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures
  6. 2022Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
  7. 2024On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures
  8. 2021UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021