| import numpy as np |
| import librosa |
|
|
| SR = 16000 |
| N_COEFFS = 20 |
|
|
| def extract_mfcc(y, sr, n_mfcc=N_COEFFS): |
| return librosa.feature.mfcc(y=y, sr=sr, n_mfcc=n_mfcc) |
|
|
| def extract_lfcc(y, sr, n_lfcc=N_COEFFS): |
| S = librosa.feature.melspectrogram(y=y, sr=sr, n_mels=n_lfcc, fmin=0, fmax=sr/2) |
| return librosa.power_to_db(S) |
|
|
| def extract_features_with_time_series(file_path, sr=SR, n_coeffs=N_COEFFS): |
| try: |
| y, _ = librosa.load(file_path, sr=sr, mono=True) |
| y, _ = librosa.effects.trim(y) |
| if np.max(np.abs(y)) > 0: |
| y = y / np.max(np.abs(y)) |
|
|
| mfccs = extract_mfcc(y, sr, n_mfcc=n_coeffs) |
| lfccs = extract_lfcc(y, sr, n_lfcc=n_coeffs) |
| chroma = librosa.feature.chroma_stft(y=y, sr=sr) |
| spec_centroid = librosa.feature.spectral_centroid(y=y, sr=sr) |
| spec_bandwidth = librosa.feature.spectral_bandwidth(y=y, sr=sr) |
| zcr = librosa.feature.zero_crossing_rate(y) |
|
|
| features_to_stack = [mfccs, lfccs, chroma, spec_centroid, spec_bandwidth, zcr] |
| max_len = max(f.shape[1] for f in features_to_stack) |
| padded = [librosa.util.fix_length(f, size=max_len, axis=1) for f in features_to_stack] |
| stacked_features = np.vstack(padded).astype(np.float32) |
| return stacked_features.T |
| except Exception as e: |
| print(f"[extract_features] Error: {e}") |
| return None |
