Audiosegment 对象和波形文件/数据之间的转换

Question

我正在从 mp3 语音文件中提取 MFCC 功能，但我确实希望保持源文件不可更改且不添加任何新文件。我的处理包括以下步骤：

• 使用pydub加载.mp3文件，消除静音，生成.wav数据
• 使用scipy.io.wavfile.read()读取音频数据和速率
• 使用python_speech_features提取特征

但是，eliminate_silence() 返回一个AudioSegment对象，而scipy.io.wavfile.read() 接受一个.wav 文件名，因此我不得不将数据临时保存/导出为波形以确保两者之间的转换。这一步是内存和耗时的，所以我的问题是：如何避免导出波形文件步骤？还是有解决方法？

这是我的代码。

import os
from pydub import AudioSegment
from scipy.io.wavfile import read
from sklearn import preprocessing
from python_speech_features import mfcc
from pydub.silence import split_on_silence

def eliminate_silence(input_path):
    """ Eliminate silent chunks from original call recording """
    # Import input wave file
    sound  = AudioSegment.from_mp3(input_path)
    chunks = split_on_silence(sound,
                              # split on silences longer than 1000ms (1 sec)
                              min_silence_len=500,
                              # anything under -16 dBFS is considered silence
                              silence_thresh=-30,
                              # keep 200 ms of leading/trailing silence
                              keep_silence=100)

    output_chunks = AudioSegment.empty()
    for chunk in chunks: output_chunks += chunk
    return output_chunks


silence_clear_data = eliminate_silence("file.mp3")
silence_clear_data.export("temp.wav", format="wav")
rate, audio = read("temp.wav")
os.remove("temp.wav")

# Extract MFCCs
mfcc_feature = mfcc(audio, rate, winlen = 0.025, winstep = 0.01, numcep = 15,
                    nfilt = 35, nfft = 512, appendEnergy = True)
mfcc_feature = preprocessing.scale(mfcc_feature)

Answer 1

我目前正在做一个项目，我使用静音和 mfcc 系数使用音频剪辑，我离开了我的解决方案：

import pydub
import python_speech_features as p
import numpy as np

def generate_mfcc_without_silences(path):
    #get audio and change frame rate to 16KHz
    audio_file = pydub.AudioSegment.from_wav(path)
    audio_file = audio_file.set_frame_rate(16000)
    #cut audio using silences
    chunks = pydub.silence.split_on_silence(audio_file, silence_thresh=audio_file.dBFS, min_silence_len=200)
    mfccs = []
    for chunk in chunks:
        #compute mfcc from chunk array
        np_chunk = np.frombuffer(chunk.get_array_of_samples(), dtype=np.int16)
        mfccs.append(p.mfcc(np_chunk, samplerate=audio_file.frame_rate, numcep=26))
    return mfccs

注意事项：

·我把音频改成 16KHz 但这是可选的

·我将 min_silence_len 的值设为 200，因为我想尝试获取单个单词

使用我的功能内容和您的要求，您需要的功能可能是：

import pydub
import python_speech_features as p
import numpy as np
from sklearn import preprocessing

def mfcc_from_audio_without_silences(path):
    audio_file  = pydub.AudioSegment.from_mp3(input_path)
    chunks = pydub.silence.split_on_silence(audio_file, silence_thresh=-30, min_silence_len=500, keep_silence=100)

    output_chunks = pydub.AudioSegment.empty()
    for chunk in chunks:
        output_chunks += chunk

    output_chunks = np.frombuffer(output_chunks.get_array_of_samples(), dtype=np.int16)
    mfcc_feature = p.mfcc(output_chunks, samplerate=audio_file.frame_rate, numcep=15, nfilt = 35)
    return preprocessing.scale(mfcc_feature)

Answer 2

看起来AudioSegment.get_array_of_samples() 是您所需要的。 （在将它传递给 mfcc 之前，您可能需要从该数组构造一个 numpy 数组。）