-
I'd like to do aspect-based sentiment analysis using a CNN. For this purpose, I not only want to feed my sentence into the network, but want to condition my network on the target aspect for which it s…
-
-
Originally reported by @pblouw:
> I've been playing around with running the speech demo over all of the test examples (n=192) by creating a bash script that repeatedly runs the demo script on diffe…
-
Dear,
In the script,
[https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/speech_commands/input_data.py](url)
is there any related pdf or other file about the mfcc feature extr…
-
getMfccFrames does the equivalent of util.audio.audiofile_to_input_vector. It relies mainly on python_speech_features.mfcc.
c_speech_features.mfcc outperforms psf's by a considerable margin when co…
-
Can someone give me an intuitive explanation of stride concept? If stride =2, will rnn skip through one step at a time for the features generated from mfcc while unrolling?
ghost updated
5 years ago
-
Hi @dogancan !
I am computing MFCC features using `kaldi.feat.mfcc.compute_feature` method to perform speech activity detection on a wav test file.
I first realized that creating a SAD object thro…
-
This issue is in part discussed in https://github.com/librosa/librosa/issues/595, however, my question is more narrow.
It is quite common in speech processing to have win_length different from n_ff…
-
您好，预处理过程中的函数world_encode_spectral_envelop我看到您的备注是# Get Mel-cepstral coefficients (MCEPs)，得到的coded_sp就等同于mcep了么，此外我还注意到您用了librosa提取mfcc但是没有使用它，这是为什么呢
-
Spotted a link ordering problem with recent GCC (reproduced on GCC 6 from Ubuntu 16.10, but not on GCC 4.9.3):
```g++ -o deepspeech `pkg-config --cflags sox` -L../../tensorflow/tensorflow//bazel-bin/…