# An RFP dataset for Real, Fake, and Partially fake audio detection

arXiv: https://arxiv.org/abs/2404.17721 · HTML: https://mlsanity.com/paper/2404.17721/

## Key facts

- Cited by 1 papers in the map (data through 20 Oct 2026).
- Placed in Anti-spoofing and adversarial audio attacks, one of 11 directions in Speech and audio language models.
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Placed in

- Speech and audio language models / [Anti-spoofing and adversarial audio attacks](https://mlsanity.com/speech/anti-spoofing-and-adversarial-audio-attacks/)

## Builds on (most cited first, 20 of 20)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [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)
- [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://mlsanity.com/paper/2006.06873/) (2020)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [ADD 2022: the First Audio Deep Synthesis Detection Challenge](https://mlsanity.com/paper/2202.08433/) (2022)
- [Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme](https://mlsanity.com/paper/2109.13821/) (2021)
- [FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion](https://mlsanity.com/paper/2210.15418/) (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)
- [Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling](https://mlsanity.com/paper/2009.02725/) (2020)
- [Half-Truth: A Partially Fake Audio Detection Dataset](https://mlsanity.com/paper/2104.03617/) (2021)
- [Towards End-to-End Synthetic Speech Detection](https://mlsanity.com/paper/2106.06341/) (2021)
- [DiPCo -- Dinner Party Corpus](https://mlsanity.com/paper/1909.13447/) (2019)
- [An Initial Investigation for Detecting Partially Spoofed Audio](https://mlsanity.com/paper/2104.02518/) (2021)
- [DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices](https://mlsanity.com/paper/2005.13770/) (2020)
- [Open Challenges in Synthetic Speech Detection](https://mlsanity.com/paper/2209.07180/) (2022)
- [Spoofing detection under noisy conditions: a preliminary investigation and an initial database](https://mlsanity.com/paper/1602.02950/) (2016)

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

- [Alethia: A Foundational Encoder for Voice Deepfakes](https://mlsanity.com/paper/2605.00251/) (2026)

## Abstract (arXiv)

Recent advances in deep learning have enabled the creation of natural-sounding synthesised speech. However, attackers have also utilised these tech-nologies to conduct attacks such as phishing. Numerous public datasets have been created to facilitate the development of effective detection models. How-ever, available datasets contain only entirely fake audio; therefore, detection models may miss attacks that replace a short section of the real audio with fake audio. In recognition of this problem, the current paper presents the RFP da-taset, which comprises five distinct audio types: partial fake (PF), audio with noise, voice conversion (VC), text-to-speech (TTS), and real. The data are then used to evaluate several detection models, revealing that the available detec-tion models incur a markedly higher equal error rate (EER) when detecting PF audio instead of entirely fake audio. The lowest EER recorded was 25.42%. Therefore, we believe that creators of detection models must seriously consid-er using datasets like RFP that include PF and other types of fake audio.