Computer_Speech_Technology/Lab/Lab2/code/test.py

from typing import Optional
import scipy.io.wavfile as wav
import numpy as np
import matplotlib.pyplot as plt
import ipdb


def hamming(frame_length: int) -> np.ndarray:
    # frame_length - 窗长

    n = np.arange(frame_length)
    h = 0.54 - 0.4 * np.cos(2 * np.pi * n / (frame_length - 1))
    return h


def delta_sgn(x: np.ndarray) -> np.ndarray:
    # x - 语音信号

    sound = x
    threshold = np.max(np.abs(sound)) / 20
    negative_sound = sound + threshold
    negative_sound -= np.abs(negative_sound)
    positive_sound = sound - threshold
    positive_sound += np.abs(positive_sound)
    sound = negative_sound + positive_sound
    return np.sign(sound)


def ampf(
    x: np.ndarray, FrameLen: Optional[int] = 128, inc: Optional[int] = 90
) -> np.ndarray:
    # x - 语音时域信号
    # FrameLen - 每一帧的长度
    # inc - 步长

    frames = []
    for i in range(0, len(x) - FrameLen, inc):
        frame = x[i : i + FrameLen]
        frames.append(frame)
    frames = np.array(frames)

    h = hamming(frame_length=FrameLen)  # 海明窗
    amp = np.dot(frames**2, h.T**2).T / FrameLen

    return amp


def zcrf(
    x: np.ndarray, FrameLen: Optional[int] = 128, inc: Optional[int] = 90
) -> np.ndarray:
    # x - 语音时域信号
    # FrameLen - 每一帧的长度
    # inc - 步长

    sound = x
    sgn_sound = np.sign(sound)

    dif_sound = np.abs(sgn_sound[1:] - sgn_sound[:-1])
    h = np.ones((FrameLen,)) / (2 * FrameLen)

    frames = []
    for i in range(0, len(dif_sound) - FrameLen, inc):
        frame = dif_sound[i : i + FrameLen]
        frames.append(frame)

    frames = np.array(frames)
    zcr = np.dot(frames, h.T).T
    return zcr


def zcrf_delta(
    x: np.ndarray, FrameLen: Optional[int] = 128, inc: Optional[int] = 90
) -> np.ndarray:
    # x - 语音时域信号
    # FrameLen - 每一帧的长度
    # inc - 步长

    sound = x
    sgn_sound = delta_sgn(sound)

    dif_sound = np.abs(sgn_sound[1:] - sgn_sound[:-1])
    h = np.ones((FrameLen,)) / (2 * FrameLen)

    frames = []
    for i in range(0, len(dif_sound) - FrameLen, inc):
        frame = dif_sound[i : i + FrameLen]
        frames.append(frame)

    frames = np.array(frames)
    zcr = np.dot(frames, h.T).T
    return zcr


def analyze_sound(
    filename: str, FrameLen: Optional[int] = 128, inc: Optional[int] = 90
) -> None:
    sr, sound_array = wav.read(filename)
    sound_array = sound_array.T[0, :] if sound_array.ndim != 1 else sound_array
    sound_array = sound_array / np.max(np.abs(sound_array))  # 归一化

    amp = ampf(sound_array, FrameLen, inc)
    zcr = zcrf_delta(sound_array, FrameLen, inc)

    rescale_rate = len(sound_array) / amp.shape[0]
    frameTime = np.arange(len(amp)) * rescale_rate

    # 边界检测
    x1 = []
    x2 = []
    x3 = []
    amp2 = np.min(amp) + (np.max(amp) - np.min(amp)) / 20
    zcr2 = np.min(zcr) + (np.max(zcr) - np.min(zcr)) / 18

    threshold_len = 6
    state = 1
    for i in range(threshold_len, len(amp) - threshold_len):
        if state == 1:
            if np.all(zcr[i : i + threshold_len] > zcr2):
                x1.append(i * rescale_rate)
                state = 2
        elif state == 2:
            if np.all(amp[i : i + threshold_len] > amp2):
                x3.append(i * rescale_rate)
                state = 3
        if (
            state != 1
            and np.all(amp[i : i + threshold_len] < amp2)
            and np.all(zcr[i : i + threshold_len] < zcr2)
        ):
            x2.append(i * rescale_rate)
            state = 1

    # 绘制语音波形、短时能量、短时过零率
    plt.figure(figsize=(12, 8))
    # 语音波形
    plt.subplot(3, 1, 1)
    plt.plot(sound_array)
    plt.title("Waveform")
    for boundary in x1:
        plt.axvline(x=boundary, color="r", linestyle="--", linewidth=0.5)
    for boundary in x2:
        plt.axvline(x=boundary, color="b", linestyle="--", linewidth=0.5)
    for boundary in x3:
        plt.axvline(x=boundary, color="g", linestyle="--", linewidth=0.5)

    # 短时能量
    plt.subplot(3, 1, 2)
    plt.plot(frameTime, amp, label="Energy")
    plt.axhline(y=amp2, color="r", linestyle="--", label="Energy Threshold")
    plt.legend()
    plt.title("Short-time Energy")
    for boundary in x1:
        plt.axvline(x=boundary, color="r", linestyle="--", linewidth=0.5)
    for boundary in x2:
        plt.axvline(x=boundary, color="b", linestyle="--", linewidth=0.5)
    for boundary in x3:
        plt.axvline(x=boundary, color="g", linestyle="--", linewidth=0.5)

    # 短时过零率
    plt.subplot(3, 1, 3)
    plt.plot(frameTime, zcr, label="Zero Crossing Rate")
    plt.axhline(y=zcr2, color="r", linestyle="--", label="ZCR Threshold")
    plt.legend()
    plt.title("Short-time Zero Crossing Rate")

    # 显示语音端点和清/浊音边界
    for boundary in x1:
        plt.axvline(x=boundary, color="r", linestyle="--", linewidth=0.5)
    for boundary in x2:
        plt.axvline(x=boundary, color="b", linestyle="--", linewidth=0.5)
    for boundary in x3:
        plt.axvline(x=boundary, color="g", linestyle="--", linewidth=0.5)

    plt.tight_layout()
    plt.show()


if __name__ == "__main__":
    analyze_sound("tang1.wav", FrameLen=128, inc=90)