-
Hello, I am trying to compute MFCC data of audio files for iOS apps using pocketshphinx. Is the TLSphinx has this feature? if yes, is there any sample code showing me how to use the framework for this…
-
Hi, I cannot make same result of librosa's mfccs. This maybe relate to #206
Librosa code:
```python
def getMfcc(file_name):
X, sample_rate = sf.read(file_name, dtype='float32')
mfccs = l…
-
波形图 -> 预加强 -> 分帧(由于人声音是非稳态,但是短时间内变化是稳态,与是在10ms内做，但是10ms这样做会导致丢失了变化趋势的特征,于是做窗口重合,由于窗口有重合 会导致做fft的时候有频谱泄露。) -> 加窗 (去掉两边重合部分的波) -> 快速傅里叶变化 ->对幅度取平方或者绝对值-> 取mel -> 取log(fbank) -> 取离散余弦变化->得到前13个包络点.(MF…
-
Hi, Do you know how to implement this data enhancement method, using fbank features instead of mfcc features?
Looking forward to your reply, thank you very much
-
I saw the closed issue asking about feature ranges and the suggestion to normalize data relative to all audio file outputs. Due to a relatively small dataset, I would like to normalize using the actua…
-
How did you train your model? Could you please provide the training file as well?
On `Data_Process.ipynb` file when calculating m, v and s you used mfcc parameters like this,
```python
audio …
-
Hello, everyone!
I run the project, and found some problem, and change code as bellow, then it works well.
1, about the mfcc_batch_generator funtion, which generate a batch of sound featur…
-
Hello,
I have problem when I run the train.py script with ASVspoof2017 data like below
I've edited extract_mfcc method in extract_feature.py because
librosa.feature.delta(mfcc) shows
**libro…
-
As Title, MFCC is not listed in Sonic Visulizer.
I am using the pre-compiled library in builds/osx/mir-edu.dylib.
-
Hello,
I am trying to replicate the MFCC output of [Librosa](https://librosa.org/doc/main/generated/librosa.feature.mfcc.html), which is widely used as the reference library for audio manipulation.…
Yaxit updated
2 years ago