Comments (4)
Thanks for the clarification -- it would make a nice addition to the paper and definitely help others reproduce your experiment.
Here is my (slightly more pytorchic) version of SincConv
that can be used as a drop-in replacement for torch.nn.Conv1d
: https://gist.github.com/hbredin/c3bfa80f8f71181c2d499167d297f181
from sincnet.
Hi Hervé,
we tried many different alternatives at this level and experiments are still running to find better solutions. For instance, we recently compared the performance with and without the abs function you pointed out. The reason why it could make sense to add an abs function here, is that standard max-pooling only looks into the positive samples of the filtered signal, while with abs we basically consider the envelope of it. This would allow the network to extract features more related to the “energy” or “envelope” of the signal, resembling “more closely” the standard pipeline used for extracting standard fbank or mfcc features. Actually, the standard fbanks is still quite different since we average the spectrum within rectangular filters. From my experiments, however, I saw that doing average pooling at this level works slightly worse than max pooling.
from sincnet.
Great job! thank you!
from sincnet.
It seems that the addition of this abs operation is very important for fast convergence!
from sincnet.
Related Issues (20)
- Hamming window simplification
- the problem with the other dataset
- loss function returns nan
- Need some idea on how to use this model to perform speaker verification task.
- DownStream (ASV: Automatic Speaker Verification) - missing information
- Question about the creation of the Sinc filterbank
- Voxceleb1 cfg file?
- Sincnet show the spectrogram is so odd ,it create so many stripe,why???? HOT 1
- CUDA error: device-side assert triggered
- .scp files for VoxCeleb1/VoxCeleb2 - how to get/generate them
- Clarifications for creating sequential batches instead of random sampling.
- cw_len
- SincNet visualization
- Is the Learning Speaker Representations with Mutual Information paper ever going to be implemented?
- How long did it take to run the Timit dataset? HOT 1
- chunk numbers in code "N_fr"
- Use of two optimizers?
- SincNet band
- Can it work on pure music?
- Difference between mfcc feature and torch tensor feature used while computing d vector? Does mfcc affect speaker identification accuracy?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sincnet.