使用librosa進行特征提取

Question

我正在使用從Github獲取以下代碼。 此代碼提取了mfccs，色度，質譜圖，tonnetz和光譜對比功能，以feat.np的形式輸出。 我想提取rmse，zerocross等其他功能，但是當我添加relevent代碼時，在連接時會出錯。

# coding= UTF-8
#
# Author: Fing
# Date  : 2017-12-03
#

import glob
import os
import librosa
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import specgram
import soundfile as sf

def extract_feature(file_name):
    X, sample_rate = sf.read(file_name, dtype='float32')
    if X.ndim > 1:
        X = X[:,0]
    X = X.T

    # short term fourier transform
    stft = np.abs(librosa.stft(X))

    # mfcc
    mfccs = np.mean(librosa.feature.mfcc(y=X, sr=sample_rate, n_mfcc=40).T,axis=0)

    # chroma
    chroma = np.mean(librosa.feature.chroma_stft(S=stft, sr=sample_rate).T,axis=0)

    # melspectrogram
    mel = np.mean(librosa.feature.melspectrogram(X, sr=sample_rate).T,axis=0)

    # spectral contrast
    contrast = np.mean(librosa.feature.spectral_contrast(S=stft, sr=sample_rate).T,axis=0)

    tonnetz = np.mean(librosa.feature.tonnetz(y=librosa.effects.harmonic(X), sr=sample_rate).T,axis=0)

    return mfccs,chroma,mel,contrast,tonnetz

def parse_audio_files(parent_dir,sub_dirs,file_ext='*.wav'):
    features, labels = np.empty((0,193)), np.empty(0)
    for label, sub_dir in enumerate(sub_dirs):
        for fn in glob.glob(os.path.join(parent_dir, sub_dir, file_ext)):
            try:
                mfccs, chroma, mel, contrast,tonnetz = extract_feature(fn)
            except Exception as e:
                print("[Error] extract feature error. %s" % (e))
                continue
            ext_features = np.hstack([mfccs,chroma,mel,contrast,tonnetz])
            print(ext_features)
            print(features)
            features = np.vstack([features,ext_features])
            # labels = np.append(labels, fn.split('/')[1])
            labels = np.append(labels, label)
        print("extract %s features done" % (sub_dir))
    return np.array(features), np.array(labels, dtype = np.int)

def one_hot_encode(labels):
    n_labels = len(labels)
    n_unique_labels = len(np.unique(labels))
    one_hot_encode = np.zeros((n_labels,n_unique_labels))
    one_hot_encode[np.arange(n_labels), labels] = 1
    return one_hot_encode

# Get features and labels
r = os.listdir("data/")
r.sort()
features, labels = parse_audio_files('data', r)
np.save('feat.npy', features)
np.save('label.npy', labels)
 `

這段代碼可以正常工作，但是當我想提取其他功能（如rmse，過零率等）時。 當我添加

#rmse=np.mean(librosa.feature.rmse(y=X).T,axis=0)

我收到以下錯誤

File "C:\Users\HP\Anaconda2\lib\site-packages\numpy\core\shape_base.py", line 237, in vstack
    return _nx.concatenate([atleast_2d(_m) for _m in tup], 0)

ValueError: all the input array dimensions except for the concatenation axis must match exactly

我如何提取其他特征並同時進行連接。

Answer 1

STFT和RMSE的形狀不同於MFCC和其他功能。 STFT和MFCC是二維的，而其他是一維的。