wblgers / py_speech_seg Goto Github PK

你好，博主，请问是怎么下载AMI数据集的呢？麻烦您有空帮忙解答以下哈

请问这个k value值是如何确定的呢？

I would like to ask why running my own recorded audio file program will cause an exception

I would appreciate it very much if you could help me solve this problem.

您好，我已经看了prepare_dataset这份代码，但是能提供一下示例的训练音频数据的格式吗 谢谢

如果一段电话录音中有一段铃声，可以自动识别并切除掉吗?
还有就是您的模型的在说话人分离的准确率上表现的怎么样呢?有统计过相应的指标吗?
谢谢!

Your output wav file is not usable in python "wave" module. Error message:
wave.Error: unknown format: 3

I do not know WAV format well , your output file in encoding with "F.P. PCM" while other working-well files are encoding with "Signed PCM".

I would appreciate it very much if you could help me solve this problem.

Traceback (most recent call last):
File "c:\Users\jiaqi.Li.vscode\extensions\ms-python.python-2019.4.12954\pythonFiles\ptvsd_launcher.py", line 43, in
main(ptvsdArgs)
File "c:\Users\jiaqi.Li.vscode\extensions\ms-python.python-2019.4.12954\pythonFiles\lib\python\ptvsd_main_.py", line 410, in main
run()
File "c:\Users\jiaqi.Li.vscode\extensions\ms-python.python-2019.4.12954\pythonFiles\lib\python\ptvsd_main_.py", line 291, in run_file
runpy.run_path(target, run_name='main')
File "D:\ProgramData\Anaconda3\lib\runpy.py", line 263, in run_path
pkg_name=pkg_name, script_name=fname)
File "D:\ProgramData\Anaconda3\lib\runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "D:\ProgramData\Anaconda3\lib\runpy.py", line 85, in run_code
exec(code, run_globals)
File "e:\moviesub_proj\py_speech_seg-master\multi_detect.py", line 11, in
cluster_method='bic')
File "e:\moviesub_proj\py_speech_seg-master\speech_segmentation.py", line 122, in multi_segmentation
y, sr = librosa.load(file, sr=sr)
File "D:\ProgramData\Anaconda3\lib\site-packages\librosa\core\audio.py", line 119, in load
with audioread.audio_open(os.path.realpath(path)) as input_file:
File "D:\ProgramData\Anaconda3\lib\site-packages\audioread_init.py", line 111, in audio_open
return BackendClass(path)
File "D:\ProgramData\Anaconda3\lib\site-packages\audioread\rawread.py", line 62, in init
self._fh = open(filename, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'E:\moviesub_proj\duihua_sample.wav'

你好，我在Windows python3.8 环境下运行错误，能不能帮我看看是什么问题，截图：

为什么BIC的公式被改为了协方差矩阵的迹了？你博客里写的是行列式呢？

请问我想找出一段语音的开头和结尾怎么做呢？

请教一下，不是很理解 wStart = wStart + detBIC + 200 中+200的含义。这样不是就跳过分割点的后200个点,默认这200点中里面没有分割点了吗？

def speech_segmentation(mfccs):
    wStart = 0
    wEnd = 200
    wGrow = 200
    delta = 25

    m, n = mfccs.shape

    store_cp = []
    index = 0
    while wEnd < n:
        featureSeg = mfccs[:, wStart:wEnd]
        detBIC = compute_bic(featureSeg, delta)
        index = index + 1
        if detBIC > 0:
            temp = wStart + detBIC
            store_cp.append(temp)
            wStart = wStart + detBIC + 200
            wEnd = wStart + wGrow
        else:
            wEnd = wEnd + wGrow

    return np.array(store_cp)

BIC = 0.5*(nnp.log(det0)-indexnp.log(det1)-(n-index)np.log(det2))-0.5(m+0.5m(m+1))*np.log(n)

就是最前面的那个0.5，我看您给的公式中并不需要乘以这个0.5

Traceback (most recent call last):
File "multi_detect.py", line 54, in
main()
File "multi_detect.py", line 26, in main
seg_point = seg.multi_segmentation(wavfile,outdir,sr,mono,frame_size,frame_s
hift,plot_seg=False,save_seg=True,classify_seg=False)
File "E:\duplicate_data\test1\speech_seg-master\speech_segmentation.py", line
112, in multi_segmentation
x1, x2 = vad.vad(temp, sr=sr, framelen=frame_size, frameshift=frame_shift)
File "E:\duplicate_data\test1\speech_seg-master\voice_activity_detect.py", lin
e 27, in vad
signs = (tmp1* tmp2) < 0
ValueError: operands could not be broadcast together with shapes (1288,256) (128
7,256)