# Audio Steganography on AudioCaps

Source: [Audio Steganography on AudioCaps](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-12T07:53:43.133Z

Evaluation of Audio Steganography performance on the AudioCaps dataset, assessed using various Bit Error Rate (BER) metrics under different compression and modification conditions.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Audio Steganography |
| Dataset (including any stated split) | AudioCaps |
| Metric | BER (Original) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [BER (Original)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(Original)>): Lower is better; unit: PERCENT.

- [BER (AAC 320k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(AAC%20320k)>): Lower is better; unit: PERCENT.

- [BER (AAC 192k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(AAC%20192k)>): Lower is better; unit: PERCENT.

- [BER (AAC 128k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(AAC%20128k)>): Lower is better; unit: PERCENT.

- [BER (AAC 64k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(AAC%2064k)>): Lower is better; unit: PERCENT.

- [BER (MP3 320k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(MP3%20320k)>): Lower is better; unit: PERCENT.

- [BER (MP3 192k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(MP3%20192k)>): Lower is better; unit: PERCENT.

- [BER (MP3 128k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(MP3%20128k)>): Lower is better; unit: PERCENT.

- [BER (MP3 64k)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(MP3%2064k)>): Lower is better; unit: PERCENT.

- [BER (Resampling Up)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(Resampling%20Up)>): Lower is better; unit: PERCENT.

- [BER (Resampling Down)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(Resampling%20Down)>): Lower is better; unit: PERCENT.

- [BER (High Attention)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(High%20Attention)>): Lower is better; unit: PERCENT.

- [BER (Low Boost)](<https://www.sota2.com/research/sota/audio-steganography-on-audiocaps.md?metric=BER%20(Low%20Boost)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | BER (Original) | Result date | Report paper |
| --- | --- | --- | --- |
| PRoADS | 0.09 | Not recorded | 69b24876d030084c22e2f837 |
| Hu | 0.11 | Not recorded | 69b24876d030084c22e2f837 |
| PRoADS | 0.12 | Not recorded | 69b24876d030084c22e2f837 |
| Hu | 0.62 | Not recorded | 69b24876d030084c22e2f837 |
| Kim | 1.44 | Not recorded | 69b24876d030084c22e2f837 |
| Kim | 1.71 | Not recorded | 69b24876d030084c22e2f837 |
| Yang | 6.55 | Not recorded | 69b24876d030084c22e2f837 |
| Yang | 7.17 | Not recorded | 69b24876d030084c22e2f837 |

### PRoADS

BER (Original): 0.09. Result ID: 69b270056dbb7075b95cc82e.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

Recorded evaluation configuration: {"Scheduler":"DDIM"}. This record does not assert independent reproduction.

### Hu

BER (Original): 0.11. Result ID: 69b270056dbb7075b95cc82d.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

Recorded evaluation configuration: {"Scheduler":"DDIM"}. This record does not assert independent reproduction.

### PRoADS

BER (Original): 0.12. Result ID: 69b270056dbb7075b95cc832.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

Recorded evaluation configuration: {"Scheduler":"DPMSolver"}. This record does not assert independent reproduction.

### Hu

BER (Original): 0.62. Result ID: 69b270056dbb7075b95cc831.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

Recorded evaluation configuration: {"Scheduler":"DPMSolver"}. This record does not assert independent reproduction.

### Kim

BER (Original): 1.44. Result ID: 69b270056dbb7075b95cc82c.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f941e209131cea46690.md>)

Recorded evaluation configuration: {"Scheduler":"DDIM"}. This record does not assert independent reproduction.

### Kim

BER (Original): 1.71. Result ID: 69b270056dbb7075b95cc830.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f941e209131cea46690.md>)

Recorded evaluation configuration: {"Scheduler":"DPMSolver"}. This record does not assert independent reproduction.

### Yang

BER (Original): 6.55. Result ID: 69b270056dbb7075b95cc82b.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73131e209131cea5a4a6.md>)

Recorded evaluation configuration: {"Scheduler":"DDIM"}. This record does not assert independent reproduction.

### Yang

BER (Original): 7.17. Result ID: 69b270056dbb7075b95cc82f.

[Reporting paper](<https://www.sota2.com/research/paper/69b24876d030084c22e2f837.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73131e209131cea5a4a6.md>)

Recorded evaluation configuration: {"Scheduler":"DPMSolver"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.