Comments (2)
Hi @srdfjy,
You are right, there is an overlap between the speakers in the train and dev, and this might affect generalization performance. Ideally, we would like to have a completely different set of speakers. However, since have limited amount of speakers (~110) and would like to: i) mix 4 or 5 different speakers simultaneously speaking; ii) generate a (relatively) large amount of training examples, we decided to allow this overlap.
Since there is not performance gap between the dev and test sets, we found that there is not generalization issue due to the speakers identity.
In case you do observe issues related to the speakers identity, you generate a mixtures dataset using Librispeech, which has much more speakers than WSJ (~2200).
from svoice.
thanks @adiyoss
from svoice.
Related Issues (20)
- RuntimeError: stack expects each tensor to be equal size HOT 3
- Execute make_dataset err(ValueError: low >= high) HOT 2
- make_dataset.py is slow to generate samples HOT 3
- fixed speaker HOT 2
- sisnr nan HOT 1
- Function 'DivBackward0' returned nan values in its 1th output HOT 2
- Anyone got good results?
- RuntimeError: Offset past EOF
- Please help me
- Pre trained model HOT 1
- How to train using TPU?
- got soundfile.LibsndfileError: <unprintable LibsndfileError object> when execute train.py HOT 7
- how to solve cuda out of memory when execute train.py ? have tried to reduce batch size to 1 but problem still persist HOT 1
- I need help with this problem: cannot import name 'get_ref_type' from 'omegaconf._utils'
- Transfer Learning/ Improving performance of the base model
- soundfile.LibsndfileError: <unprintable LibsndfileError object> HOT 2
- Modify the Loss function for Partial/or non overlapping data.
- Access is denied error
- TypeError: cannot unpack non-iterable AudioMetaData object HOT 1
- Invalid argument: num_frames must be -1 or greater than 0. 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 svoice.