Table 4 Comparison of different watermarking techniques in terms of their objective (SNR) and subjective (MOS) measurements, capacity (bps), EER (%), and identification rate (%)
From: Semi-fragile digital speech watermarking for online speaker recognition
Watermark techniques | MOS speechb | Speech SNR (dB) | MOS musica | Capacity (bps) | EER (%) | Identification rate (%) |
|---|---|---|---|---|---|---|
Semi-fragile DWPT-QIM | 5 | 43.39 | 5 | 31.25–1000 | 20.23 | 66.43 |
AbS [25] | 4.11 | 28.08 | 3.22 | 33.33–50 | 27.23 | 52.98 |
4.67 | 30.32 | 3.10 | 33.33–50 | 23.14 | 62.76 | |
DT-CWT [22] | 4.88 | 31.36 | 3.45 | 15.66–976.56 | 39.58 | 46.37 |
Genetic algorithm [26] | 4.51 | 29.30 | 3.56 | N/A | 42.23 | 49.38 |