目录
  • 文档 >
  • 音频数据增强 >
  • 旧版本 (稳定版)
快捷方式
tutorials/audio_data_augmentation_tutorial

注意

点击 此处 下载完整的示例代码

音频数据增强

**作者**：Moto Hira

torchaudio 提供多种增强音频数据的方法。

在本教程中，我们将探讨如何应用效果、滤波器、RIR（房间脉冲响应）和编解码器。

最后，我们将合成来自干净语音的电话上的噪声语音。

import torch
import torchaudio
import torchaudio.functional as F

print(torch.__version__)
print(torchaudio.__version__)

import matplotlib.pyplot as plt

2.5.0
2.5.0

准备

首先，我们导入模块并下载本教程中使用的音频资源。

from IPython.display import Audio

from torchaudio.utils import download_asset

SAMPLE_WAV = download_asset("tutorial-assets/steam-train-whistle-daniel_simon.wav")
SAMPLE_RIR = download_asset("tutorial-assets/Lab41-SRI-VOiCES-rm1-impulse-mc01-stu-clo-8000hz.wav")
SAMPLE_SPEECH = download_asset("tutorial-assets/Lab41-SRI-VOiCES-src-sp0307-ch127535-sg0042-8000hz.wav")
SAMPLE_NOISE = download_asset("tutorial-assets/Lab41-SRI-VOiCES-rm1-babb-mc01-stu-clo-8000hz.wav")

  0%|          | 0.00/427k [00:00<?, ?B/s]
100%|##########| 427k/427k [00:00<00:00, 56.9MB/s]

  0%|          | 0.00/31.3k [00:00<?, ?B/s]
100%|##########| 31.3k/31.3k [00:00<00:00, 34.5MB/s]

  0%|          | 0.00/78.2k [00:00<?, ?B/s]
100%|##########| 78.2k/78.2k [00:00<00:00, 61.6MB/s]

应用效果和滤波

torchaudio.io.AudioEffector 允许以类似于 ffmpeg 命令的方式直接将滤波器和编解码器应用于 Tensor 对象。

AudioEffector 用法 <./effector_tutorial.html> 解释了如何使用此类，因此有关详细信息，请参阅本教程。

# Load the data
waveform1, sample_rate = torchaudio.load(SAMPLE_WAV, channels_first=False)

# Define effects
effect = ",".join(
    [
        "lowpass=frequency=300:poles=1",  # apply single-pole lowpass filter
        "atempo=0.8",  # reduce the speed
        "aecho=in_gain=0.8:out_gain=0.9:delays=200:decays=0.3|delays=400:decays=0.3"
        # Applying echo gives some dramatic feeling
    ],
)


# Apply effects
def apply_effect(waveform, sample_rate, effect):
    effector = torchaudio.io.AudioEffector(effect=effect)
    return effector.apply(waveform, sample_rate)


waveform2 = apply_effect(waveform1, sample_rate, effect)

print(waveform1.shape, sample_rate)
print(waveform2.shape, sample_rate)

torch.Size([109368, 2]) 44100
torch.Size([144642, 2]) 44100

请注意，应用效果后，帧数和通道数与原始音频不同。让我们听听音频。

def plot_waveform(waveform, sample_rate, title="Waveform", xlim=None):
    waveform = waveform.numpy()

    num_channels, num_frames = waveform.shape
    time_axis = torch.arange(0, num_frames) / sample_rate

    figure, axes = plt.subplots(num_channels, 1)
    if num_channels == 1:
        axes = [axes]
    for c in range(num_channels):
        axes[c].plot(time_axis, waveform[c], linewidth=1)
        axes[c].grid(True)
        if num_channels > 1:
            axes[c].set_ylabel(f"Channel {c+1}")
        if xlim:
            axes[c].set_xlim(xlim)
    figure.suptitle(title)

def plot_specgram(waveform, sample_rate, title="Spectrogram", xlim=None):
    waveform = waveform.numpy()

    num_channels, _ = waveform.shape

    figure, axes = plt.subplots(num_channels, 1)
    if num_channels == 1:
        axes = [axes]
    for c in range(num_channels):
        axes[c].specgram(waveform[c], Fs=sample_rate)
        if num_channels > 1:
            axes[c].set_ylabel(f"Channel {c+1}")
        if xlim:
            axes[c].set_xlim(xlim)
    figure.suptitle(title)

原始

plot_waveform(waveform1.T, sample_rate, title="Original", xlim=(-0.1, 3.2))
plot_specgram(waveform1.T, sample_rate, title="Original", xlim=(0, 3.04))
Audio(waveform1.T, rate=sample_rate)
  • Original
  • Original


应用效果

plot_waveform(waveform2.T, sample_rate, title="Effects Applied", xlim=(-0.1, 3.2))
plot_specgram(waveform2.T, sample_rate, title="Effects Applied", xlim=(0, 3.04))
Audio(waveform2.T, rate=sample_rate)
  • Effects Applied
  • Effects Applied


模拟房间混响

卷积混响 是一种用于使干净音频听起来像是产生在不同环境中的技术。

例如，使用房间脉冲响应 (RIR)，我们可以使干净语音听起来像是发出在会议室中。

对于此过程，我们需要 RIR 数据。以下数据来自 VOiCES 数据集，但您可以自己录制——只需打开麦克风并拍手即可。

rir_raw, sample_rate = torchaudio.load(SAMPLE_RIR)
plot_waveform(rir_raw, sample_rate, title="Room Impulse Response (raw)")
plot_specgram(rir_raw, sample_rate, title="Room Impulse Response (raw)")
Audio(rir_raw, rate=sample_rate)
  • Room Impulse Response (raw)
  • Room Impulse Response (raw)


首先，我们需要清理 RIR。我们提取主脉冲并根据其功率对其进行归一化。

rir = rir_raw[:, int(sample_rate * 1.01) : int(sample_rate * 1.3)]
rir = rir / torch.linalg.vector_norm(rir, ord=2)

plot_waveform(rir, sample_rate, title="Room Impulse Response")
Room Impulse Response

然后，使用 torchaudio.functional.fftconvolve()，我们将语音信号与 RIR 进行卷积。

speech, _ = torchaudio.load(SAMPLE_SPEECH)
augmented = F.fftconvolve(speech, rir)

原始

plot_waveform(speech, sample_rate, title="Original")
plot_specgram(speech, sample_rate, title="Original")
Audio(speech, rate=sample_rate)
  • Original
  • Original


应用 RIR

plot_waveform(augmented, sample_rate, title="RIR Applied")
plot_specgram(augmented, sample_rate, title="RIR Applied")
Audio(augmented, rate=sample_rate)
  • RIR Applied
  • RIR Applied


添加背景噪声

为了将背景噪声引入音频数据，我们可以根据某些所需的信噪比 (SNR) [维基百科] 将噪声 Tensor 添加到表示音频数据的 Tensor，该比率决定了输出中音频数据相对于噪声的强度。

$$ \mathrm{SNR} = \frac{P_{signal}}{P_{noise}} $$

$$ \mathrm{SNR_{dB}} = 10 \log _{{10}} \mathrm {SNR} $$

为了根据 SNR 添加噪声到音频数据，我们使用 torchaudio.functional.add_noise()。

speech, _ = torchaudio.load(SAMPLE_SPEECH)
noise, _ = torchaudio.load(SAMPLE_NOISE)
noise = noise[:, : speech.shape[1]]

snr_dbs = torch.tensor([20, 10, 3])
noisy_speeches = F.add_noise(speech, noise, snr_dbs)

背景噪声

plot_waveform(noise, sample_rate, title="Background noise")
plot_specgram(noise, sample_rate, title="Background noise")
Audio(noise, rate=sample_rate)
  • Background noise
  • Background noise


SNR 20 dB

snr_db, noisy_speech = snr_dbs[0], noisy_speeches[0:1]
plot_waveform(noisy_speech, sample_rate, title=f"SNR: {snr_db} [dB]")
plot_specgram(noisy_speech, sample_rate, title=f"SNR: {snr_db} [dB]")
Audio(noisy_speech, rate=sample_rate)
  • SNR: 20 [dB]
  • SNR: 20 [dB]


SNR 10 dB

snr_db, noisy_speech = snr_dbs[1], noisy_speeches[1:2]
plot_waveform(noisy_speech, sample_rate, title=f"SNR: {snr_db} [dB]")
plot_specgram(noisy_speech, sample_rate, title=f"SNR: {snr_db} [dB]")
Audio(noisy_speech, rate=sample_rate)
  • SNR: 10 [dB]
  • SNR: 10 [dB]


SNR 3 dB

snr_db, noisy_speech = snr_dbs[2], noisy_speeches[2:3]
plot_waveform(noisy_speech, sample_rate, title=f"SNR: {snr_db} [dB]")
plot_specgram(noisy_speech, sample_rate, title=f"SNR: {snr_db} [dB]")
Audio(noisy_speech, rate=sample_rate)
  • SNR: 3 [dB]
  • SNR: 3 [dB]


将编解码器应用于 Tensor 对象

torchaudio.io.AudioEffector 还可以将编解码器应用于 Tensor 对象。

waveform, sample_rate = torchaudio.load(SAMPLE_SPEECH, channels_first=False)


def apply_codec(waveform, sample_rate, format, encoder=None):
    encoder = torchaudio.io.AudioEffector(format=format, encoder=encoder)
    return encoder.apply(waveform, sample_rate)

原始

plot_waveform(waveform.T, sample_rate, title="Original")
plot_specgram(waveform.T, sample_rate, title="Original")
Audio(waveform.T, rate=sample_rate)
  • Original
  • Original


8 位 μ-law

mulaw = apply_codec(waveform, sample_rate, "wav", encoder="pcm_mulaw")
plot_waveform(mulaw.T, sample_rate, title="8 bit mu-law")
plot_specgram(mulaw.T, sample_rate, title="8 bit mu-law")
Audio(mulaw.T, rate=sample_rate)
  • 8 bit mu-law
  • 8 bit mu-law


G.722

g722 = apply_codec(waveform, sample_rate, "g722")
plot_waveform(g722.T, sample_rate, title="G.722")
plot_specgram(g722.T, sample_rate, title="G.722")
Audio(g722.T, rate=sample_rate)
  • G.722
  • G.722


Vorbis

vorbis = apply_codec(waveform, sample_rate, "ogg", encoder="vorbis")
plot_waveform(vorbis.T, sample_rate, title="Vorbis")
plot_specgram(vorbis.T, sample_rate, title="Vorbis")
Audio(vorbis.T, rate=sample_rate)
  • Vorbis
  • Vorbis


模拟电话录音

结合前面的技术，我们可以模拟听起来像一个人在回声室里通过电话交谈，同时还有人在背景中交谈的音频。

sample_rate = 16000
original_speech, sample_rate = torchaudio.load(SAMPLE_SPEECH)

plot_specgram(original_speech, sample_rate, title="Original")

# Apply RIR
rir_applied = F.fftconvolve(speech, rir)

plot_specgram(rir_applied, sample_rate, title="RIR Applied")

# Add background noise
# Because the noise is recorded in the actual environment, we consider that
# the noise contains the acoustic feature of the environment. Therefore, we add
# the noise after RIR application.
noise, _ = torchaudio.load(SAMPLE_NOISE)
noise = noise[:, : rir_applied.shape[1]]

snr_db = torch.tensor([8])
bg_added = F.add_noise(rir_applied, noise, snr_db)

plot_specgram(bg_added, sample_rate, title="BG noise added")

# Apply filtering and change sample rate
effect = ",".join(
    [
        "lowpass=frequency=4000:poles=1",
        "compand=attacks=0.02:decays=0.05:points=-60/-60|-30/-10|-20/-8|-5/-8|-2/-8:gain=-8:volume=-7:delay=0.05",
    ]
)

filtered = apply_effect(bg_added.T, sample_rate, effect)
sample_rate2 = 8000

plot_specgram(filtered.T, sample_rate2, title="Filtered")

# Apply telephony codec
codec_applied = apply_codec(filtered, sample_rate2, "g722")
plot_specgram(codec_applied.T, sample_rate2, title="G.722 Codec Applied")
  • Original
  • RIR Applied
  • BG noise added
  • Filtered
  • G.722 Codec Applied

原始语音

Audio(original_speech, rate=sample_rate)


应用 RIR

Audio(rir_applied, rate=sample_rate)


添加背景噪声

Audio(bg_added, rate=sample_rate)


滤波

Audio(filtered.T, rate=sample_rate2)


应用编解码器

Audio(codec_applied.T, rate=sample_rate2)


**脚本总运行时间：**（0 分钟 14.991 秒）

由 Sphinx-Gallery 生成的图库

文档

访问 PyTorch 的全面开发者文档

查看文档

教程

获取初学者和高级开发人员的深入教程

查看教程

资源

查找开发资源并获得问题的解答

查看资源

为了分析流量并优化您的体验，我们在本网站上使用 Cookie。点击或浏览即表示您同意我们使用 Cookie。作为本网站的当前维护方，Facebook 的 Cookie 政策适用。了解更多信息，包括可用的控制选项：Cookie 政策。