Comments (16)
Please read the following posts for further information:
What's state of the art for speaker recognition and verification?
Is there any open source deep learning tool available for speaker recognition?
For speaker recognition, what are the best ML algorithms? What are the features that I should get from a voice?
How can I understand the speaker recognition, speaker identification and speaker verification?
https://www.quora.com/What-are-some-speaker-recognition-toolkits
from 3d-convolutional-speaker-recognition.
I try ai-shell dataset the kaldi i-vector is around 2% eer.
But this 3D-convolutional-speaker-recognition is 20% eer.
I think it is not a so novel model actually.
from 3d-convolutional-speaker-recognition.
@SpongebBob , how can you get 20% eer in the evaluation phase, do you reuse this code?
from 3d-convolutional-speaker-recognition.
@duynguyen5896
I think one sample per speaker is not too much for training the background model.
What do you mean by unenrollment??
The samples for evaluations cannot project the correct statistics as well
from 3d-convolutional-speaker-recognition.
@duynguyen5896 more details #33
from 3d-convolutional-speaker-recognition.
@SpongebBob Please make sure to do the correct experiments ... This is a deep learning method and for a new dataset, it needs a lot of tweaking.
from 3d-convolutional-speaker-recognition.
@SpongebBob Please reopen #33 if the problem has not been resolved.
from 3d-convolutional-speaker-recognition.
@astorfi, unenrollment mean that rejection ( i don't enroll those people) and want to recognize if the model can classify them or not.
For the samples for evaluations, how many samples you use for evaluation per person?
from 3d-convolutional-speaker-recognition.
@SpongebBob can you update your evaluation source code? I don't understand how you evaluate the model through the #33.
from 3d-convolutional-speaker-recognition.
@duynguyen5896 I don't think SpongebBob did a similar experimental setup for 3D-Conv and Kaldi i-vector. 2% EER is not very realistic for 0.8 seconds of data and text-independent setting.
About VoxCeleb, I am trying to use Pytorch for the same setup. However, the VoxCeleb is huge and parameter tuning does not seem to be trivial.
from 3d-convolutional-speaker-recognition.
@astorfi Can you give me more detail about your experiment in enrollment and evaluation phase, i can see in your paper that you used 100 speakers for enrollment and evaluation.
Did you enroll all 100 speakers?
from 3d-convolutional-speaker-recognition.
Yes, all 100 speakers are enrolled. In the evaluation, different enrollments of the same speakers are used.
from 3d-convolutional-speaker-recognition.
@astorfi , For the enrollment phase, i see that you merge 20 utterances of 1 speaker. Are those utterances selected randomly or they are the continuous chain of speech?
I tried to enroll all 100 speakers and 50 enrolled-50 not enrolled for testing. However, the results are not good for both, the result seem to be regardless to the number of enrolled speakers, they are still about 40% EER
from 3d-convolutional-speaker-recognition.
@duynguyen5896 For selecting utterances, either of the cases works. However, I did that selection randomly.
May I know why you are splitting like that? 50 enrolled and 50 unenrolled?
I think you are making a mistake. Please read the paper as I have to emphasize once again.
All 100 speakers must be used in enrollment and evaluation stages as we are comparing the known speakers with the speaker models. For unenrolled subjects, we do not have any model since this model is not end-to-end. Please make sure that you understand the speaker verification setup we are using.
from 3d-convolutional-speaker-recognition.
@astorfi Actually, i want to try if the model can predict unenrolled well or not. However, when i do the same setup as you, 100 enrolled the result also not good. I think the reason is different dataset.
Anyway, thank for your help and kindness.
I'm trying if the model work well on small dataset. I have a small dataset (only 46 speakers) and i want to try if the result will be better or not when using 10 utterances per sample. How you setup the 10 utterances model structure?
from 3d-convolutional-speaker-recognition.
@duynguyen5896 Yes, unfortunately, the dataset is not public and tune it for a new dataset needs tuning.
I don't think it works for small datasets.
from 3d-convolutional-speaker-recognition.
Related Issues (20)
- Convolution expects input with rank 4, got 5 HOT 9
- Extracting VAD for our own dataset HOT 1
- How to generate data HOT 13
- Run time error in the demo HOT 6
- No such file or directory: 'results/SCORES/score_vector.npy HOT 1
- Where does input_feature.py store it's results? HOT 1
- How to make Speaker Verification (1:1 recognition) model in keras? HOT 1
- What is the exact meaning of "utterances"? HOT 4
- ValueError: axes don't match array
- What does low-level and high-level features extraction mean? HOT 1
- .wav inputs specifics HOT 6
- where is score_vector.npy HOT 2
- Demo video recording link is broken
- Please update the vedio link of the demo.
- Pre trained model HOT 1
- Does anyone know the EER of this repo? HOT 1
- How to deal with .hdfs5 files ? HOT 2
- version problem HOT 1
- Speakers for Enrollment and Development
- γAll Dependency of This Project HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from 3d-convolutional-speaker-recognition.