python

关注公众号 jb51net

关闭
首页 > 脚本专栏 > python > python 音频重采样

python 音频处理重采样、音高提取的操作方法

作者:io_T_T

这篇文章主要介绍了python 音频处理重采样、音高提取,本文给大家介绍的非常详细,感兴趣的朋友跟随小编一起看看吧

采集数据->采样率调整

import torch
 import torchaudio
 from torchaudio.transforms import Resample
 from time import time#仅计算时间,不影响主体

封装一下,总函数【记得先导入】:

def resample_by_cpu():
    file_path = input("please input your file path: ")
    start_time = time()#不影响,可去掉
    y, sr = torchaudio.load(file_path)  #使用torchaudio.load导入音频文件
​
    target_sample = 32000   #设定目标采样率
    resampler = Resample(orig_freq=sr, new_freq=target_sample)#构造resample函数,输入原始采样率和目标采样率
    resample_misic = resampler(y)                             #调用resample函数
​
    torchaudio.save("test.mp3", resample_misic, target_sample)#调用torchaudio的保存即可
    print(f"cost :{time() - start_time}s")#不影响,可去掉

最后结果大概是几秒钟这样子

2.使用使用torchaudio进行重采样(gpu版):

有了上面cpu的基础,其实调用gpu也就更换一下设备,和放入gpu的操作就好了,因此不过多赘述

def resample_use_cuda():
​
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    start_time = time()
    file_path = input("please input your file path:")
    y, sr = torchaudio.load(file_path)
​
    y = y.to(device)
    target_sample = 32000
    resampler = Resample(orig_freq=sr, new_freq=target_sample).to(device)
    resample_misic = resampler(y)
    torchaudio.save("test.mp3", resample_misic.to('cpu'), target_sample)    #这里注意要把结果从gpu中拿出来到cpu,不然会报错。
    print(f"cost :{time() - start_time}s")

时间方面嘛,单个音频多了放入gpu取出gpu的步骤肯定会稍慢的,但是跑过cuda都知道它的强大,更多是用于后续的操作说是。

3.使用librosa库进行重采样

具体步骤:

import librosa
import soundfile as sf
from time import time#仅计算时间,不影响主体

综合封装成函数:

def resample_by_lisa():
    file_path = input("please input your file path:")
    start_time = time()
    y, sr = librosa.load(file_path)     #使用librosa导入音频文件
    target_sample_rate = 32000
    y_32k = librosa.resample(y=y, orig_sr=sr, target_sr=target_sample_rate)         #使用librosa进行重采样至目标采样率
    sf.write("test_lisa.mp3", data=y_32k, samplerate=target_sample_rate)        #使用soundfile进行文件写入
    print(f"cost :{time() - start_time}s")

总结:

all code:

import torch
import torchaudio
from torchaudio.transforms import Resample
import librosa
import soundfile as sf
from time import time
​
def resample_by_cpu():
    file_path = input("please input your file path: ")
    start_time = time()
    y, sr = torchaudio.load(file_path)  #使用torchaudio.load导入音频文件
​
    target_sample = 32000   #设定目标采样率
    resampler = Resample(orig_freq=sr, new_freq=target_sample)#构造resample函数,输入原始采样率和目标采样率
    resample_misic = resampler(y)                             #调用resample函数
​
    torchaudio.save("test.mp3", resample_misic, target_sample)#调用torchaudio的保存即可
    print(f"cost :{time() - start_time}s")
def resample_use_cuda():
​
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    start_time = time()
    file_path = input("please input your file path:")
    y, sr = torchaudio.load(file_path)
​
    y = y.to(device)
    target_sample = 32000
    resampler = Resample(orig_freq=sr, new_freq=target_sample).to(device)
    resample_misic = resampler(y)
    torchaudio.save("test.mp3", resample_misic.to('cpu'), target_sample)
    print(f"cost :{time() - start_time}s")
​
def resample_by_lisa():
    file_path = input("please input your file path:")
    start_time = time()
    y, sr = librosa.load(file_path)#使用librosa导入音频文件
    target_sample_rate = 32000
    y_32k = librosa.resample(y=y, orig_sr=sr, target_sr=target_sample_rate)#使用librosa进行重采样至目标采样率
    sf.write("test_lisa.mp3", data=y_32k, samplerate=target_sample_rate)#使用soundfile进行文件写入
    print(f"cost :{time() - start_time}s")
​
if __name__ == '__main__':
    resample_use_cuda()
    resample_by_cpu()
    resample_by_lisa()

2.2 提取pitch基频特征【音高提取】

使用torchaudio进行基频特征提取

其实主要使用的这个函数:torchaudio.transforms._transforms.PitchShift

让我们来看看它官方的example,仿照着来写就好啦

>>> waveform, sample_rate = torchaudio.load("test.wav", normalize=True)
>>> transform = transforms.PitchShift(sample_rate, 4)
>>> waveform_shift = transform(waveform)  # (channel, time)

步骤:

import torchaudio
import torchaudio.transforms as Tf
import matplotlib.pyplot as plt     #画图依赖

code:

def get_pitch_by_torch():
    file_path = input("file path:")
    y, sr = torchaudio.load(file_path)
    """specimen:
    >>> waveform, sample_rate = torchaudio.load("test.wav", normalize=True)
    >>> transform = transforms.PitchShift(sample_rate, 4)
    >>> waveform_shift = transform(waveform)  # (channel, time)
    """
    pitch_tf = Tf.PitchShift(sample_rate=sr, n_steps=0)
    feature = pitch_tf(y)
    # 绘制基频特征 这部分可以忽略,只是画图而已,可以直接复制不用理解
    plt.figure(figsize=(16, 5))
    plt.plot(feature[0].numpy(), label='Pitch')
    plt.xlabel('Frame')
    plt.ylabel('Frequency (Hz)')
    plt.title('Pitch Estimation')
    plt.legend()
    plt.show()

输出图片【总歌曲】效果:

将输出的范围稍微改一下,切分特征的一部分,就是歌曲部分的音高特征啦,效果就很明显了

改为:plt.plot(feature[0][5000:10000].numpy(), label='Pitch')

使用librosa提取基频特征

主要函数:librosa.pyin,请见官方example

#Computing a fundamental frequency (F0) curve from an audio input
>>> y, sr = librosa.load(librosa.ex('trumpet'))
>>> f0, voiced_flag, voiced_probs = librosa.pyin(y,
...                                              sr=sr,
...                                              fmin=librosa.note_to_hz('C2'),
...                                              fmax=librosa.note_to_hz('C7'))
>>> times = librosa.times_like(f0, sr=sr)

code:

def get_pitch_by_librosa():
​
    file_path = input("请输入音频文件路径:")
    y, sr = librosa.load(file_path)
    """librosa.pyin(y,sr=sr,fmin=librosa.note_to_hz('C2'),fmax=librosa.note_to_hz('C7'))"""
    # 使用pyin提取基频特征
    f0, voiced_flag, voiced_probs = librosa.pyin(y, sr=sr, fmin=librosa.note_to_hz('C2'), fmax=librosa.note_to_hz('C7'))
​
    # 绘制基频特征,可忽略
    plt.figure(figsize=(14, 5))
    librosa.display.waveshow(y, sr=sr, alpha=0.5)
    plt.plot(librosa.times_like(f0), f0, label='f0 (fundamental frequency)', color='r')
    plt.xlabel('Time (s)')
    plt.ylabel('Frequency (Hz)')
    plt.title('Pitch (fundamental frequency) Estimation')
    plt.legend()
    plt.show()

总结:

输出:

all code:

import torchaudio
import torchaudio.transforms as Tf
import matplotlib.pyplot as plt
import librosa
def get_pitch_by_torch():
    file_path = input("file path:")
    y, sr = torchaudio.load(file_path)
    """specimen:
    >>> waveform, sample_rate = torchaudio.load("test.wav", normalize=True)
    >>> transform = transforms.PitchShift(sample_rate, 4)
    >>> waveform_shift = transform(waveform)  # (channel, time)
    """
    pitch_tf = Tf.PitchShift(sample_rate=sr, n_steps=0)
    feature = pitch_tf(y)
    # 绘制基频特征
    plt.figure(figsize=(16, 5))
    plt.plot(feature[0][5000:10000].numpy(), label='Pitch')
    plt.xlabel('Frame')
    plt.ylabel('Frequency (Hz)')
    plt.title('Pitch Estimation')
    plt.legend()
    plt.show()
def get_pitch_by_librosa():
​
    file_path = input("请输入音频文件路径:")
    y, sr = librosa.load(file_path)
    """librosa.pyin(y,sr=sr,fmin=librosa.note_to_hz('C2'),fmax=librosa.note_to_hz('C7'))"""
    # 使用pyin提取基频特征
    f0, voiced_flag, voiced_probs = librosa.pyin(y, sr=sr, fmin=librosa.note_to_hz('C2'), fmax=librosa.note_to_hz('C7'))
​
    # 绘制基频特征,可忽略
    plt.figure(figsize=(14, 5))
    librosa.display.waveshow(y, sr=sr, alpha=0.5)
    plt.plot(librosa.times_like(f0), f0, label='f0 (fundamental frequency)', color='r')
    plt.xlabel('Time (s)')
    plt.ylabel('Frequency (Hz)')
    plt.title('Pitch (fundamental frequency) Estimation')
    plt.legend()
    plt.show()
if __name__ == '__main__':
    # get_pitch_by_torch()
    # get_pitch_by_librosa()

后续PPG特征、vec特征见下一章 

到此这篇关于python 音频处理重采样、音高提取的文章就介绍到这了,更多相关python 音频重采样内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家!

您可能感兴趣的文章:
阅读全文