def add_noise()

in avhubert/hubert_dataset.py [0:0]

• 28 lines of code
• 10 McCabe index (conditional complexity)

    def add_noise(self, clean_wav):
        clean_wav = clean_wav.astype(np.float32)
        noise_wav = self.select_noise()
        if type(self.noise_snr) == int or type(self.noise_snr) == float:
            snr = self.noise_snr
        elif type(self.noise_snr) == tuple:
            snr = np.random.randint(self.noise_snr[0], self.noise_snr[1]+1)
        clean_rms = np.sqrt(np.mean(np.square(clean_wav), axis=-1))
        if len(clean_wav) > len(noise_wav):
            ratio = int(np.ceil(len(clean_wav)/len(noise_wav)))
            noise_wav = np.concatenate([noise_wav for _ in range(ratio)])
        if len(clean_wav) < len(noise_wav):
            start = 0
            noise_wav = noise_wav[start: start + len(clean_wav)]
        noise_rms = np.sqrt(np.mean(np.square(noise_wav), axis=-1))
        adjusted_noise_rms = clean_rms / (10**(snr/20))
        adjusted_noise_wav = noise_wav * (adjusted_noise_rms / noise_rms)
        mixed = clean_wav + adjusted_noise_wav

        #Avoid clipping noise
        max_int16 = np.iinfo(np.int16).max
        min_int16 = np.iinfo(np.int16).min
        if mixed.max(axis=0) > max_int16 or mixed.min(axis=0) < min_int16:
            if mixed.max(axis=0) >= abs(mixed.min(axis=0)): 
                reduction_rate = max_int16 / mixed.max(axis=0)
            else :
                reduction_rate = min_int16 / mixed.min(axis=0)
            mixed = mixed * (reduction_rate)
        mixed = mixed.astype(np.int16)
        return mixed