Function calculate_fft

machine_learning/mfcc.py:218–251

Calculate the Fast Fourier Transform (FFT) of windowed audio data. Args: audio_windowed: The windowed audio signal. ftt_size: The size of the FFT (default is 1024). Returns: The FFT of the audio data. Examples: >>> audio_windowed = np.array([[1.0, 2.0,

(audio_windowed: np.ndarray, ftt_size: int = 1024)

def calculate_fft(audio_windowed: np.ndarray, ftt_size: int = 1024) -> np.ndarray:
    """
    Calculate the Fast Fourier Transform (FFT) of windowed audio data.

    Args:
        audio_windowed: The windowed audio signal.
        ftt_size: The size of the FFT (default is 1024).

    Returns:
        The FFT of the audio data.

    Examples:
    >>> audio_windowed = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
    >>> audio_fft = calculate_fft(audio_windowed, ftt_size=4)
    >>> bool(np.allclose(audio_fft[0], np.array([6.0+0.j, -1.5+0.8660254j,
    ...     -1.5-0.8660254j])))
    True
    """
    # Transpose the audio data to have time in rows and channels in columns
    audio_transposed = np.transpose(audio_windowed)

    # Initialize an array to store the FFT results
    audio_fft = np.empty(
        (int(1 + ftt_size // 2), audio_transposed.shape[1]),
        dtype=np.complex64,
        order="F",
    )

    # Compute FFT for each channel
    for n in range(audio_fft.shape[1]):
        audio_fft[:, n] = fft.fft(audio_transposed[:, n], axis=0)[: audio_fft.shape[0]]

    # Transpose the FFT results back to the original shape
    return np.transpose(audio_fft)


def calculate_signal_power(audio_fft: np.ndarray) -> np.ndarray: