Comments (5)
Can you please show an example? Wonder how often it's that different; which mel bin is most different; etc.
from lhotse.
I don't know how much useful it can be, but here are some plots for now ( I can compute also some stats on the difference distribution). There is a difference of over 3.9 for one bin and it is very strange.
Loaded mixture feats:
On the fly np.log(np.sum(np.exp(c_sources), 0) + np.exp(c_noise)):
Abs difference between the two:
from lhotse.
from lhotse.
Thank you very much.
I'll try to train two systems (when i will have some spare GPUs) for separation in feature domain.
One with mixing on-the-fly as above and one without and see what happens. In the past I have always mixed the features on-the-fly and had decent results.
My main concern is that it is sorta like using "noisy labels" for separation.
And because the separation is done on mels (and not in log-mels) those differences actually can be even more substantial and it could be difficult for the DNN to learn a mask for each speaker with that amount of "noise" in the oracle targets.
from lhotse.
I'm closing as it seems stale - if there're any new developments be sure to let us know!
from lhotse.
Related Issues (20)
- How to split manifests into several parts HOT 1
- Pytorch dataloader cannot compute length HOT 2
- Create a custom audio transformation HOT 1
- Describe on cuts does not display supervision custom info
- PR #1332 breaks many operations HOT 1
- 'ascii' codec can't encode characters in position 219-247 in processing wenet speech dateset HOT 1
- Multiple feature extractors in a single Cut HOT 1
- AttributeError: 'dict' object has no attribute 'to_dict' HOT 2
- error in window 11 installation HOT 1
- UnicodeEncodeError: 'ascii' codec can't encode characters in position 505-506: ordinal not in range(128) HOT 2
- OSError: [Errno 9] Unable to synchronously open file (unable to lock file, errno = 9, error message = 'Bad file descriptor') HOT 1
- Support for Video Features, for example How2Sign HOT 7
- dataloader slow with shar HOT 3
- Feature calculation process crashing with large dataset HOT 1
- How to combine with huggingface audio datasets? HOT 1
- AudioTransforms are dropped when saving MixedCuts? HOT 2
- How does tar work with DynamicBucketingSampler?
- Read seperate .jsonl.gz from fbank filter them and make a Cutset into single variable. HOT 3
- How to load parquet file effectively with Lhotse? HOT 1
- MUSAN mix to current CutSet: Cannot load audio of cuts in a lazy CutSet. HOT 3
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 lhotse.