---
license: mit
tags:
  - audio
  - anti-spoofing
  - audio-deepfake-detection
  - speech
  - asvspoof
  - wav2vec2
---

# XLSR-SLS

[![EER% 0.23 on ASVspoof2019_LA](https://img.shields.io/badge/EER%25%20on%20ASVspoof2019__LA-0.23%25-brightgreen)](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls)
[![EER% 7.39 on ASVspoof2021_LA](https://img.shields.io/badge/EER%25%20on%20ASVspoof2021__LA-7.39%25-yellow)](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls)
[![EER% 3.93 on ASVspoof2021_DF](https://img.shields.io/badge/EER%25%20on%20ASVspoof2021__DF-3.93%25-green)](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls)
[![EER% 7.46 on InTheWild](https://img.shields.io/badge/EER%25%20on%20InTheWild-7.46%25-yellow)](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls)
[![EER% 9.81 on CD-ADD](https://img.shields.io/badge/EER%25%20on%20CD-ADD-9.81%25-yellow)](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls)
[![arena tier](https://img.shields.io/endpoint?url=https://speechantispoofingbenchmarks-speechantispoofingarena.hf.space/badge/xlsr-sls/tier.json)](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls)
[![arena rank](https://img.shields.io/endpoint?url=https://speechantispoofingbenchmarks-speechantispoofingarena.hf.space/badge/xlsr-sls/rank.json)](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls)

A **wav2vec 2.0 (XLS-R 300M) + SLS** audio-deepfake-detection model, from
*"Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier"*
(Zhang, Wen & Hu, **ACM MM 2024**). A self-supervised XLS-R front-end is paired
with the **SLS (Sensitive Layer Selection)** classifier, which treats the 24
XLS-R transformer layers as a feature pyramid and learns to weight them. The
model takes a raw speech waveform and returns a score where **higher = more
bona fide**.

- **Code:** https://github.com/QiShanZhang/SLSforASVspoof-2021-DF
- **Paper:** https://doi.org/10.1145/3664647.3681345 (ACM MM 2024; no arXiv version)
- **Parameters:** 340,790,000 (340.79 M)
- **Checkpoint:** [`MMpaper_model.pth`](./MMpaper_model.pth) (the paper's released model)

The exact wrapper used to produce the Arena scores is in
[`xlsr_sls.py`](./xlsr_sls.py); the network definition is in [`_net.py`](./_net.py).

## Architecture

1. **wav2vec 2.0 XLS-R (300M) front-end** — a self-supervised transformer
   (`fairseq` `Wav2Vec2Model`) producing 1024-d frame features from **all 24
   transformer layers**.
2. **SLS (Sensitive Layer Selection) back-end** — every layer's hidden state is
   average-pooled to a 1024-d descriptor and gated by a per-layer **sigmoid
   attention** (`fc0` → sigmoid); the gates re-weight the full per-layer feature
   stack, which is summed across layers. The fused feature passes through
   BatchNorm + SELU + `3×3` max-pool, is flattened, and goes through a two-layer
   MLP (`fc1: 22847→1024`, `fc3: 1024→2`).
3. The 2-class **log-softmax** output is read at **index 1 = bona fide**.

## How it was trained

- **Data:** ASVspoof 2019 **Logical Access (LA)**.
- **Input length:** raw audio at 16 kHz cropped/padded to **64,600 samples**
  (~4.04 s). The window length is **fixed** — `fc1` expects a 22,847-d flatten,
  so the 64,600-sample window is mandatory at inference.
- **Output:** 2-class log-softmax; the bona-fide log-prob (index 1) is the score.

See the [source repository](https://github.com/QiShanZhang/SLSforASVspoof-2021-DF)
for the full training and evaluation code.

## Benchmark result (Speech Anti-Spoofing Arena)

Evaluated through the reproducible [Speech Anti-Spoofing Arena](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=xlsr-sls).
Scores were computed with a **deterministic first-64,600-sample window** (no random
crop), so the numbers are exactly reproducible from the pinned score file.
**Arena standing: 🥇 gold tier, rank #1 of 10.**

| Dataset | Split | EER % | Trials | Skipped | W2V2-AASIST† | Notes |
|---|---|---|---|---|---|---|
| ASVspoof2019_LA | test | **0.23** | 71,237 | 0 | 0.22 | in-domain (training data) |
| ASVspoof2021_LA | test | **7.39** | 181,566 | 0 | 8.11 | cross-dataset generalization |
| ASVspoof2021_DF | test | **3.93** | 611,829 | 0 | 8.32 | cross-dataset generalization |
| InTheWild | test | **7.46** | 31,779 | 0 | 11.22 | out-of-domain (real-world deepfakes) |
| CD-ADD | test | **9.81** | 20,786 | 0 | 38.57 | out-of-domain (modern neural-TTS) |

† Same benchmark, the other XLS-R-based system (XLS-R 300M + AASIST). XLSR-SLS's
multi-layer SLS fusion wins on **every out-of-domain set** — most strikingly on
**ASVspoof2021_DF (3.93 vs 8.32)** and **CD-ADD (9.81 vs 38.57)** — and is on par
in-domain. The benchmark's ASVspoof2021 LA/DF use curated trial sets, so absolute
EER differs from the paper's official-keys numbers (1.92 % DF, 7.46 % InTheWild —
the latter matched here exactly); the relative ordering is the meaningful comparison.

## Usage

The checkpoint is a `state_dict` for the `Model` network defined in
[`_net.py`](./_net.py). Constructing the network requires the base XLS-R 300M
checkpoint **`xlsr2_300m.pt`** (only used to build the wav2vec 2.0 architecture;
every weight is then overwritten by `MMpaper_model.pth`):

```bash
wget https://dl.fbaipublicfiles.com/fairseq/wav2vec/xlsr2_300m.pt
```

The input **must** be exactly 64,600 samples at 16 kHz mono — window the waveform
with `pad_fixed` (first 64,600 samples, tile-repeat if shorter).

```python
import numpy as np
from xlsr_sls import XLSRSLS   # _net.py + xlsr_sls.py are in this repo

m = XLSRSLS()
m.load()                                          # loads MMpaper_model.pth (+ xlsr2_300m.pt)
audio = np.random.randn(48000).astype(np.float32) # float32 mono 16 kHz
print(m.score_batch([audio], [16000])[0])         # higher = more bona fide
m.unload()
```

Internally the wrapper windows the input, runs the network, and returns
`output[:, 1]` (class 1 = bona fide; source `main.py`: `batch_score =
batch_out[:, 1]`). [`xlsr_sls.py`](./xlsr_sls.py) is the exact
`speech_spoof_bench` model that produced the Arena `scores.txt`.

## Citation

```bibtex
@inproceedings{zhang2024audio,
  title={Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier},
  author={Zhang, Qishan and Wen, Shuangbing and Hu, Tao},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  pages={6765--6773},
  year={2024},
  doi={10.1145/3664647.3681345}
}
```

## License

MIT — see the [source repository](https://github.com/QiShanZhang/SLSforASVspoof-2021-DF).