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

arXiv: https://arxiv.org/abs/2309.16954 · HTML: https://mlsanity.com/paper/2309.16954/

## Key facts

- Cited by 1 papers 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.

## Placed in

- Speech and audio language models / [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/)

## Builds on (most cited first, 23 of 23)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection](https://mlsanity.com/paper/2109.00537/) (2021)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection](https://mlsanity.com/paper/2107.12710/) (2021)
- [STC Antispoofing Systems for the ASVspoof2019 Challenge](https://mlsanity.com/paper/1904.05576/) (2019)
- [A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection](https://mlsanity.com/paper/2103.11326/) (2021)
- [Replay and Synthetic Speech Detection with Res2net Architecture](https://mlsanity.com/paper/2010.15006/) (2020)
- [Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?](https://mlsanity.com/paper/2106.12914/) (2021)
- [ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks](https://mlsanity.com/paper/1904.01120/) (2019)
- [Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders](https://mlsanity.com/paper/2210.10570/) (2022)
- [SASV 2022: The First Spoofing-Aware Speaker Verification Challenge](https://mlsanity.com/paper/2203.14732/) (2022)
- [Deepfake audio detection by speaker verification](https://mlsanity.com/paper/2209.14098/) (2022)
- [The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challenge](https://mlsanity.com/paper/2207.07510/) (2022)
- [Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker Verification Systems](https://mlsanity.com/paper/2206.09103/) (2022)
- [Optimizing Tandem Speaker Verification and Anti-Spoofing Systems](https://mlsanity.com/paper/2201.09709/) (2022)
- [SASV Based on Pre-trained ASV System and Integrated Scoring Module](https://mlsanity.com/paper/2207.00150/) (2022)
- [Multi-task Learning Based Spoofing-Robust Automatic Speaker Verification System](https://mlsanity.com/paper/2012.03154/) (2020)
- [Estimating the confidence of speech spoofing countermeasure](https://mlsanity.com/paper/2110.04775/) (2021)
- [Invertible Voice Conversion](https://mlsanity.com/paper/2201.10687/) (2022)

## Built on by (most cited first, 1 of 1)

- [Leveraging Gradient Reversal Loss and Multitask Learning for Datasets-Aware Audio Deepfake Detection](https://mlsanity.com/paper/2607.23961/) (2026)

## 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.