-
### Framing, Windowing
- Framing ; 전체 신호 중 한번의 FFT를 수행할 영역 추출
- Windowing : 추출된 frame에 시간에 따른 가중치 부여
- Hamming window : 불연속점이 채워지기 때문에 샘플링된 신호는 마치 연속적인 것처럼 나타남
![image](https://user-images.githu…
-
https://www.dropbox.com/sh/tzjffxkpw6jorui/OckMbMl9ZK
I generated them using the commands explained at http://labrosa.ee.columbia.edu/matlab/rastamat/ in the examples.
- train-subsample-c.txt corres…
-
Could you update this: https://github.com/d4r3topk/comparing-audio-files-python/blob/master/mfcc.py
It's addressed here: https://github.com/pierre-rouanet/dtw/pull/19/commits/307fe721a58cb475324517…
-
When I set numbands with fluid-mfcc i get following error:
I actually don't get why, is this a bug?
-
```
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
AudioDispatcher dispa…
-
In the class Mfcc.cpp, you have this function "calculate()",
32 std::vector Mfcc::calculate(const SignalSource &source,
33 std::size_t numFeatures)
…
-
Could you please add the 'mfcc_vec.npy' in this repo? Thank you~
-
# MFCCs - ratsgo's speechbook
articles about speech recognition
[https://ratsgo.github.io/speechbook/docs/fe/mfcc](https://ratsgo.github.io/speechbook/docs/fe/mfcc)
-
用torchaudio替换librosa,使用项目数据集训练模型后,推理报错:RuntimeError: running_mean should contain 344 elements not 128
推理代码如下:
with torch.no_grad():
waveform, sample_rate = torchaudio.load("data/valid…
-
Hey, first of all, great work!
Two things bug me though:
1. What's the semantic value of the HuBERT model you trained if it's using the first RVQ layer of the _acoustic_ tokenizer? I.e. the acoust…