Comments (14)
It is the one-hot speaker embedding.
from autopst.
Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery
from autopst.
Do you mean SEA?
You refer to the SEA paper for training details.
from autopst.
I seem to have fallen into a mistake. Actually , in preparing data , the Encoder part of SEA model just be used. But I'm not sure that changing the speaker will make a difference.
from autopst.
Does it matter if I take my own data and extract the features from the SEA model of 82 speakers that you pre-trained
from autopst.
Do you mean SEA?
You refer to the SEA paper for training details.
Yeah, sorry for spelling mistake
from autopst.
The performance might degrade, but feel free to try.
from autopst.
The performance might degrade, but feel free to try.
So the right thing to do is to train an SEA model with my own data and then extract the features. Could the sea part training code be provided?
from autopst.
The majority of the code for SEA is here. You just need a data loader and an optimizer.
from autopst.
The majority of the code for SEA is here. You just need a data loader and an optimizer.
OK, do you use the loss function like
from autopst.
Yes
from autopst.
@auspicious3000 what is c_trg
in model_sea.Generator.forward
? It is part of Decoder's LSTM, dimension is same as hparams.dim_spk
which is 82, but still no idea how to get it ...
from autopst.
Do you mean SEA?
You refer to the SEA paper for training details.
Hi! Could you point me to the SEA paper? I want to make sure I am reading the right one
from autopst.
@auspicious3000
Could you check my codes of SEA training loss below:
mask_sp_real = ~sequence_mask(len_real, cep_real0.size(1))# cep_real0 is MFCC that do not cut by [:, 0:20]
mask = (~mask_sp_real).float()
self.P = self.P.train()
mel_outputs , mel_outputs_B= self.P(cep_real, spk_emb, mask)#mel_outputs_B is output of decoder with input of self Expressing autoencoded Z
loss_A = F.mse_loss(mel_outputs, cep_real0,reduction='mean')
loss_B = F.mse_loss(mel_outputs_B, cep_real0,reduction='mean')
p_loss = loss_A + loss_B
from autopst.
Related Issues (18)
- ModuleNotFoundError: No module named 'onmt' HOT 1
- KeyError when run prepare_train_data.py HOT 2
- How to solve SEA model problem
- the speech content of converted voice with my own trained model changed HOT 2
- SpeechSplit actually better than AutoPST for seen speakers? HOT 1
- Missing basic execution with different set of speakers. HOT 4
- Error while running demo.ipynd
- How can we generate test_vctk.meta? HOT 5
- Issue with stop prediction for longer utterances. HOT 1
- test_vctk.meta HOT 5
- Unable to reproduce results HOT 1
- License of this repository and model HOT 3
- How to test AutoPST in onother languages? HOT 6
- How to make 'mfcc_stats.pkl' and 'spk2emb_82.pkl'? HOT 3
- How to find mean and std of MFCC? HOT 8
- 請問我該如何解決 repeats has to be Long tensor 的問題?(How to solve a problem) HOT 2
- Inference with new input audio HOT 4
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 autopst.