Comments (8)
Yes, d-vectors are all assumed to have been L2 normalized.
And yes, you are correct, von Mises–Fisher distribution might be a better distribution here to use for UIS-RNN.
We just used Normal distribution as an approximation here due to its simplicity.
from uis-rnn.
thanks for replying so fast! :)
from uis-rnn.
I was struggling to overfit a single utterance segmentation without prior L2-normalization. I will let you know if now overfitting works as expected
from uis-rnn.
With L2-normalized speaker embeddings, given a single sequence to overfit (with only two speakers and some silence speaker), uis-rnn improves upon the initial accuracy (~35%) to ~55%, but does not reach higher accuracies. I'm using default transition_bias
estimation and sigma2
initialization and adjustment.
from uis-rnn.
One more question: what is the semantics of "segments"? "nonoverlapping segments with max length of 400ms."?
from uis-rnn.
One more question: what is the semantics of "segments"? "nonoverlapping segments with max length of 400ms."?
Yes. Also, it really doesn't have to be 400ms. The length 400ms is what we found that works well on our dev / eval datasets.
from uis-rnn.
One more question about speaker embeddings. Are their values non-negative (i.e. ReLU is used prior to averaging / L2-normalization)?
I'm reimplementing a spectral clustering baseline from https://arxiv.org/abs/1710.10468 and https://github.com/wq2012/SpectralCluster, and depending on whether the values can be negative, the diffusion step may or may not be interpreted as random walk posterior probability after one step.
from uis-rnn.
They can be negative. We don't have ReLU after the last 256-dim linear layer.
from uis-rnn.
Related Issues (20)
- Embedding Extraction Procedure HOT 1
- about model HOT 1
- [Bug] Predict method does not finish HOT 3
- what is train data format? HOT 1
- Question about custom data generator
- uis-rnn gives different result on broken audios and continuous audios HOT 5
- how to control the number of different speaker when predicting? HOT 1
- Unable to convert pytorch model to tensorflow in Diarization on mobile device. HOT 2
- Change input size HOT 1
- No module named coverage HOT 1
- Is is possible to pre-load the model for multiple request? HOT 1
- [Question] About num_non_zero HOT 1
- [Question] The dimension of toy test data [test_sequence] is (25, 95, 256) what does the first 2 dimension represent? Toy train data [train_sequence] has dimension (4627, 256) which is understandable. HOT 1
- Is there a way to fine tune an already existing pre-trained model? HOT 1
- rnn initial state trainable HOT 1
- Any documentations on training from scratch using custom data in other languages ? HOT 1
- [Bug] Making a prediction on CPU after training on GPU
- Predicted labels doesn't match with Ground truth labels but the accuracy of test results is 0.8% HOT 1
- assign gpu with arguments
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 uis-rnn.