Comments (2)
hi @dandelioner
Thank you for attempting to reproduce our experiments.
The default parameters in experiment_tcd_audio.py
are not the ones that we used in the ICMI 2018 work. I will list them below for better reproducibility.
encoder_units_per_layer=((), (256, 256, 256)),
cell_type='lstm',
decoder_units_per_layer=(256, ),
optimiser='Adam', # because we removed the support for AMSGrad due to a bug
On the Speaker Dependent (SD) partition of TCD-TIMIT I normally train the models for 400 epochs at a learning rate of 0.001 and an additional 100 epochs at 0.0001. Decaying the learning rate typically results in a substantial increase of accuracy on the test set (5-8%).
In case there is still a difference between your values and ours, I can think of two other reasons.
-The experiments for ICMI 2018 were run in last year in March, when we used an older version of the OpenFace toolkit to detect and align the faces. With OpenFace 2.0 we now get a 99% detection rate even on the more challenging LRS2 dataset.
-Locally I was able to fix several label errors, there were many problems with the videos of volunteer 42M in particular. Unfortunately I do not have write access to the public repository of TCD-TIMIT to update the files there as well. However I don't expect to see a difference larger than 1% because of this aspect.
Please let me know if this fully answers your question.
from avsr-tf1.
Hi @georgesterpu
Thank you for your reply, it's very helpful for me.
After I change the parameters, I get the result: 20.54%(cer)/44.04%(wer). It's very close to the result in paper.
from avsr-tf1.
Related Issues (20)
- Inquiry about some parameter selection reason HOT 5
- awgn: out of bounds when sampling noise clip HOT 1
- [AMSGrad] get running error in audio only training HOT 3
- How do I change loss function to CTC?? HOT 2
- [feature] minimum data length for stack log mel feature HOT 2
- visemes and phonemes mapping HOT 1
- How can i change this av_align model for applying to audio2video?
- What should I do to reproduce the results of the paper? HOT 5
- How can I solve this problem HOT 6
- Inquiry about aus csv generation HOT 2
- What do the folders speaker-dependence and speaker-independence stand for? HOT 2
- How to run this program on multiple GPUs HOT 5
- The tfrecord files HOT 8
- use video-only on LRS2 HOT 1
- The result in noisy environment HOT 6
- KeyError: 'aus' when running run_audiovisual.py HOT 2
- how to pad features and labels to same length in one batch ? HOT 1
- Ask about epochs and learning rate HOT 1
- ask about the results HOT 9
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 avsr-tf1.