diff --git a/README.md b/README.md
index fad8f03..f065963 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,7 @@ num_samples = sr * 5
 transforms = [
     RandomResizedCrop(n_samples=num_samples),
     RandomApply([PolarityInversion()], p=0.8),
-    RandomApply([Noise(min_snr=0.001, max_snr=0.005)], p=0.3),
+    RandomApply([Noise(min_snr=-60, max_snr=-46)], p=0.3),
     RandomApply([Gain()], p=0.2),
     HighLowPass(sample_rate=sr), # this augmentation will always be applied in this aumgentation chain!
     RandomApply([Delay(sample_rate=sr)], p=0.5),
@@ -43,7 +43,7 @@ We can also define a stochastic augmentation on multiple transformations. The fo
 ```python
 transforms = [
     RandomResizedCrop(n_samples=num_samples),
-    RandomApply([PolarityInversion(), Noise(min_snr=0.001, max_snr=0.005)], p=0.8),
+    RandomApply([PolarityInversion(), Noise(min_snr=-60, max_snr=-46)], p=0.8),
     RandomApply([Gain()], p=0.2),
     RandomApply([Delay(sample_rate=sr), Reverb(sample_rate=sr)], p=0.5)
 ]
diff --git a/tests/test_augmentations.py b/tests/test_augmentations.py
index e15ce09..acc25b2 100644
--- a/tests/test_augmentations.py
+++ b/tests/test_augmentations.py
@@ -179,7 +179,7 @@ def test_gain(num_channels):
 def test_noise(num_channels):
     audio = generate_waveform(sample_rate, num_samples, num_channels)
     transform = Compose(
-        [Noise(min_snr=0.5, max_snr=1)],
+        [Noise(min_snr=-6, max_snr=0)],
     )
 
     t_audio = transform(audio)
diff --git a/tests/test_readme_example.py b/tests/test_readme_example.py
index ce71f73..5ef8bdb 100644
--- a/tests/test_readme_example.py
+++ b/tests/test_readme_example.py
@@ -29,7 +29,7 @@ def test_readme_example():
     transforms = [
         RandomResizedCrop(n_samples=num_samples),
         RandomApply([PolarityInversion()], p=0.8),
-        RandomApply([Noise(min_snr=0.3, max_snr=0.5)], p=0.3),
+        RandomApply([Noise(min_snr=-10, max_snr=-6)], p=0.3),
         RandomApply([Gain()], p=0.2),
         RandomApply([HighLowPass(sample_rate=sr)], p=0.8),
         RandomApply([Delay(sample_rate=sr)], p=0.5),
diff --git a/torchaudio_augmentations/augmentations/noise.py b/torchaudio_augmentations/augmentations/noise.py
index 668a495..86c7fd1 100644
--- a/torchaudio_augmentations/augmentations/noise.py
+++ b/torchaudio_augmentations/augmentations/noise.py
@@ -4,10 +4,10 @@
 
 
 class Noise(torch.nn.Module):
-    def __init__(self, min_snr=0.0001, max_snr=0.01):
+    def __init__(self, min_snr=-80, max_snr=-40):
         """
-        :param min_snr: Minimum signal-to-noise ratio
-        :param max_snr: Maximum signal-to-noise ratio
+        :param min_snr: Minimum signal-to-noise ratio in dB.
+        :param max_snr: Maximum signal-to-noise ratio in dB.
         """
         super().__init__()
         self.min_snr = min_snr
@@ -15,7 +15,8 @@ def __init__(self, min_snr=0.0001, max_snr=0.01):
 
     def forward(self, audio):
         std = torch.std(audio)
-        noise_std = random.uniform(self.min_snr * std, self.max_snr * std)
+        snr = random.uniform(self.min_snr, self.max_snr)
+        noise_std = 10**(snr/20) * std
 
         noise = np.random.normal(0.0, noise_std, size=audio.shape).astype(np.float32)