Comments (3)
It helps convergence. You can see the alignment improved when adding cumulative attention states on the 4th floor of this issue keithito/tacotron#170 (comment). I have made series of ablation studies to confirm it.
from tacotron-2.
Hello @StevenZYj, thanks for reaching out!
As stated by @begeekmyfriend, attention weights cumulation is a must to get proper alignments. This was actually stated in the paper as well:
"We use the location-sensitive attention from [21], which extends the additive attention mechanism [22] to use cumulative attention weights from previous decoder time steps as an additional feature. This encourages the model to move forward consistently through the input, mitigating potential failure modes where some subsequences are repeated or ignored by the decoder."
While the entire attention mechanism was just referenced in few words in the paper, by using the references they provide we managed to get a sense of what they are talking about. I believe what confirms this cumulation approach is the fact that when doing ablation studies (By the way great work @begeekmyfriend you never cease to impress!), we found out that when we don't use weights cumulation, the decoder tends to repeat of ignore some subsequences.
from tacotron-2.
@begeekmyfriend @Rayhane-mamah Thanks a lot! It's my bad that the point is actually in the tacotron 2 paper.
from tacotron-2.
Related Issues (20)
- Type of sequence_length in BiLSTM
- Preprocessing Error occurring for using custom dataset
- Preprocess problem HOT 1
- Linear Projection
- Speech synthesis in a language not found in the dataset
- Question: How can I train the model on my own data HOT 2
- About Loss Function and Preprocessing
- Why do we need to shuffle data in one particular batch?
- 2 different questions in 1 issue
- Errors in training WaveNet
- Is it possible to do quick and custom evaluation?
- when i run training
- is there anyway to implement garbage collection ?
- Trouble with using pretrained checkpoints HOT 1
- Can Someone please provide any pre-trained checkpoints for this model to do the transfer learning?
- Has anyone deployed this model on web before? Need some help with that? If anyone has kindly provide the steps. It's urgent
- Saving the entire model
- BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending HOT 1
- hparams.py and error with " python preprocess.py "
- ValueError: please enter a valid model to train: ['Tacotron', 'WaveNet', 'Tacotron-2'] HOT 2
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 tacotron-2.