Preprocessing the Audio Dataset (original) (raw)

Last Updated : 14 Apr, 2026

Audio preprocessing is an essential step in preparing audio data for machine learning models.

Importance of Audio Preprocessing

Preprocessing helps improve model performance and ensures consistency across datasets.

Implementation

Step 1: Install Required Libraries

pip install gdown librosa

Step 2: Import Required Libraries

import librosa from scipy.signal import butter, filtfilt import numpy as np import os import matplotlib.pyplot as plt import librosa.display

`

Step 3: Load Dataset

file_id = '1lNUGw8VMXvY2Yu6aITYlOCNaj8y-KbNB'

!gdown --id $file_id -O dataset.zip !unzip -q dataset.zip -d /content/

`

Step 4: Resampling

sample_audio_path = '/content/barbie_vs_puppy/barbie/barbie_4.wav'

def resample_audio(audio_path, target_sr=16000): y, sr = librosa.load(audio_path, sr=target_sr) return y, sr

resampled_audio, sr = resample_audio(sample_audio_path) print(f"Sample rate after Resampling: {sr}")

`

**Output:

output

output

Step 5: Filtering

Removes high-frequency noise using a low-pass filter

Python `

def butter_lowpass_filter(data, cutoff_freq, sample_rate, order=4): nyquist = 0.5 * sample_rate normal_cutoff = cutoff_freq / nyquist b, a = butter(order, normal_cutoff, btype='low', analog=False) filtered_data = filtfilt(b, a, data) print(f"Filtered audio shape: {filtered_data.shape}") return filtered_data

filtered_audio = butter_lowpass_filter(resampled_audio, cutoff_freq=4000, sample_rate=sr)

`

Step 6: Convert to Model Input

def convert_to_model_input(y, target_length): if len(y) < target_length: y = np.pad(y, (0, target_length - len(y))) else: y = y[:target_length] return y

model_input = convert_to_model_input(filtered_audio, target_length=16000) print(f"Model input shape: {model_input.shape}")

`

**Output:

output2

Output

Step 7: Audio Data Streaming (Batch Processing)

def stream_audio_dataset(dataset_path, batch_size=32, target_length=16000, target_sr=None): audio_files = [os.path.join(root, file) for root, dirs, files in os.walk(dataset_path) for file in files] np.random.shuffle(audio_files)

for i in range(0, len(audio_files), batch_size):
    batch_paths = audio_files[i:i + batch_size]
    batch_data = []

    for file_path in batch_paths:
        y, sr = librosa.load(file_path, sr=target_sr)

        if target_sr is not None and sr != target_sr:
            y = librosa.resample(y, sr, target_sr)
            sr = target_sr

        filtered_audio = butter_lowpass_filter(y, cutoff_freq=4000, sample_rate=sr)
        model_input = convert_to_model_input(filtered_audio, target_length=target_length)
        batch_data.append(model_input)

    yield np.array(batch_data)

dataset_path = '/content/barbie_vs_puppy/barbie'

for batch_data in stream_audio_dataset(dataset_path, batch_size=2, target_sr=16000): print(f"Processing batch with {len(batch_data)} files") print(f"Shape of the first file: {batch_data[0].shape}")

`

**Output:

output3

Output

Step 8: Log-Mel Spectrogram

def compute_logmel_spectrogram(y, sr, n_mels=128, hop_length=512): mel_spectrogram = librosa.feature.melspectrogram(y=y, sr=sr, n_mels=n_mels, hop_length=hop_length) logmel_spectrogram = librosa.power_to_db(mel_spectrogram, ref=np.max) return logmel_spectrogram

audio_file_path = '/content/barbie_vs_puppy/barbie/barbie_4.wav' target_sr = 16000

y, sr = librosa.load(audio_file_path, sr=target_sr) logmel_spectrogram = compute_logmel_spectrogram(y, sr=sr)

plt.figure(figsize=(8, 4)) librosa.display.specshow(logmel_spectrogram, sr=sr, hop_length=512, x_axis='time', y_axis='mel') plt.colorbar(format='%+2.0f dB') plt.title('Log-Mel Spectrogram') plt.show()

`

**Output:

output4

Log-Mel Spectogram

Download full code from here

Applications