Comments (19)
In your paper, uirnn includes 3 steps: a)Speaker Change Detection (SCD), b)Speaker Assignment Process (SAP), c) Sequence Generation
Step c) is necessary to complete the probability distribution
Yes, you use P(X,Y,Z), a generative approach. Other researches use discriminative approach P(Y|X) = P(Y|Z,X) * P(Z|X) = SAP * SCD. I think generative approach P(X,Y,Z) is nearly optimal when you can train it on extremely big dataset as Transformer based algorithms such as BERT, GPT2
UIS-RNN is our initial effort to solve the problem of clustering sequential data in a supervised way.
In unsupervised way, i found that your Spectral Cluster algorithm works quite good in many audios.
from uis-rnn.
Yes, you use P(X,Y,Z), a generative approach. Other researches use discriminative approach P(Y|X) = P(Y|Z,X) * P(Z|X) = SAP * SCD. I think generative approach P(X,Y,Z) is nearly optimal when you can train it on extremely big dataset as Transformer based algorithms such as BERT, GPT2
It's a good point. I think that's an interesting direction for future efforts.
In unsupervised way, i found that your Spectral Cluster algorithm works quite good in many audios.
Indeed, spectral clustering is by far the best unsupervised approach that we found. The only drawback is that it's a bit sensitive to its parameters. So we usually tune the parameters for specific domains that we want to deploy the system to.
from uis-rnn.
Hi,
We haven't tested uis-rnn on AMI. We found the audio quality of this dataset not good enough so we didn't use it. About the poor performance on AMI, it's likely due to the nature of LSTM/GRU not being able to handle ultra long sequences.
I also read all your code about uirnn, i don't understand 1> why do you split up the original utterances and concatenate them by speaker and then use that input for training? 2> Why doese the input ignore which audio the utterance belongs to, just merge all utterances in 1 single audio? .This process seems completely different to inference process and also reduce the capacity of using batch size if one speaker talk too much.
@AnzCol I think you can answer these better than me.
from uis-rnn.
Hi @wq2012 ,
Actually i have 2 more questions.
- If "the nature of LSTM/GRU not being able to handle ultra long sequences", did you try to use The Transformer for Sequence Generation part?
- In your paper, uirnn includes 3 steps: a)Speaker Change Detection, b)Speaker Assignment Process, c) Sequence Generation. Do you think step a,b are enough for diarization task or algorithm which basic idea is about cluster data using data order? what is the benefit of step c and is the loss function good enough to control what it can learn? Do you guarantee what distribution space it learns in training set similar to distribution space in test set?
from uis-rnn.
If "the nature of LSTM/GRU not being able to handle ultra long sequences", did you try to use The Transformer for Sequence Generation part?
I'm not familiar with that :(
In your paper, uirnn includes 3 steps: a)Speaker Change Detection, b)Speaker Assignment Process, c) Sequence Generation. Do you think step a,b are enough for diarization task or algorithm which basic idea is about cluster data using data order? what is the benefit of step c and is the loss function good enough to control what it can learn? Do you guarantee what distribution space it learns in training set similar to distribution space in test set?
Step c) is necessary to complete the probability distribution.
UIS-RNN is our initial effort to solve the problem of clustering sequential data in a supervised way. And it's definitely not necessarily the optimal approach. There are lots of directions for future improvements. If you feel skeptical about some setups in our experiments or codebase, you may have found a promising direction for future research :)
from uis-rnn.
@wq2012
Can you send me any logs for your training uirnn model since i do not know my training correct or not? have you try to predict your model on AMI dataset or ICSI corpus?
from uis-rnn.
@wrongbattery Sorry I didn't keep any of those logs. But I can usually see the loss function decreasing and finally converging.
We never had any success on AMI dataset. The acoustic condition of AMI is really different from our typical training data for training Voice Activity Detector, speaker recognition model, and UIS-RNN. Specifically, the volume of AMI dataset is really low. VAD has super large false reject.
ICSI is a great dataset. I don't remember whether we tried to predict on it (very likely not). But we tried to train on it and predict on other datasets, and it worked pretty well.
from uis-rnn.
this is my log file training on ICSI dataset. the loss just get stuck nearly around -750-> -720. I also implement based on your code allowing number of clusters as input, but the result on some youtube audios are no good. what is your max size of sequence length?
screenlog.txt
from uis-rnn.
It's weird that the loss becomes NAN at some point:
Iter: 39090 Training Loss: -728.4636
Negative Log Likelihood: 108.5799 Sigma2 Prior: -837.4142 Regularization: 0.3708
Iter: 39100 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Not sure what is going on. I didn't try to run diarization experiments on YouTube data, since I don't have any well annotated YouTube datasets. But I've heard other teams complaining that diarization on YouTube is super difficult. Personally I haven't heard of any success stories on diarization with YouTube yet.
The experiments we carried out are mostly on audios <5 minutes.
from uis-rnn.
I think your model converge quite fast after a few iterations. If we know the oracle number of speakers before hand, does spectral cluster far better than uis-rnn? Do you agree with this?
"for long conversation, uis-rnn explodes the number of predicted speakers."
from uis-rnn.
If we know the oracle number of speakers before hand, does spectral cluster far better than uis-rnn?
I don't know. We currently don't have a good implementation in uis-rnn to limit the number of speakers. We haven't tried much in this direction.
Also, if you know the number of speakers before hand, it is no longer the STANDARD speaker diarization problem. Comparing uis-rnn and spectral clustering in this case might not be very fair.
Besides, the performance of uis-rnn significantly depends on the quality of training data.
Do you agree with this?
"for long conversation, uis-rnn explodes the number of predicted speakers."
It could be true. But I wouldn't be too assertive to say this. Our current uis-rnn implementation is more of a prototype than a product. It's not mature. There are still lots of spaces to improve, and for other researchers to contribute.
from uis-rnn.
Thanks. Your idea about each network for each speaker is quite interesting. i'm trying to solve online diarization problem on production environment
from uis-rnn.
Describe the question
In Diarization task, i train on AMI train-dev set and ICSI corpus , i test on AMI test set. Both datasets include audios of 3-5 speakers in 50-70 minutes. My d embedding trains on Voxceleb1,2 with EER = 4.55%.
Hello,
May I know how many epoch you use to reach this EER 4.55%? I use 500 but it stuck at EER 18%
Really thanks
from uis-rnn.
Dear @BarCodeReader,
actually, i use sgd momentum as my optimizer, i manually decrease the learning rate when the loss doesn't change much. My input training is 250ms utterance, that mean i randomly sample from the long utterance. Actually dataset is Voxceleb1,2 , vtck, librispeech, timit, some diarization dataset
from uis-rnn.
Hi @wrongbattery,
Thanks for the info..
250 ms...ok then i need to reduce my size...i think your input size is different from the paper, but i will give a try.
other than this, you set everything the same as the paper? like 64 speakers, 10 utterances for each...
really thanks for your reply.
from uis-rnn.
@wrongbattery ICSI is a great dataset. I don't remember whether we tried to predict on it (very likely not). But we tried to train on it and predict on other datasets, and it worked pretty well.
Hi! I've divided interviews from ICSI into approx 5 minute wavs and tried to use d-vectors from https://github.com/CorentinJ/Real-Time-Voice-Cloning for training uis-rnn. But I have the same problem: loss becomes Nan at some point. Can you tell me what kind of d-vectors have you used?
from uis-rnn.
Hi! I've divided interviews from ICSI into approx 5 minute wavs and tried to use d-vectors from https://github.com/CorentinJ/Real-Time-Voice-Cloning for training uis-rnn. But I have the same problem: loss becomes Nan at some point. Can you tell me what kind of d-vectors have you used?
@innarid
Please add some print/log commands in your code and share some logs with us, otherwise it's impossible for us to debug this. Specifically:
- Which line produced the NaN?
- Which operation produced the NaN?
- What's the input of that operation?
from uis-rnn.
@innarid
i use this one for D vector, but i customize it
https://github.com/HarryVolek/PyTorch_Speaker_Verification
from uis-rnn.
@wq2012
I also met the loss becomes NaN issue, but from initial iterations. These are some first lines:
Iter: 0 Training Loss: nan
Negative Log Likelihood: 112.0798 Sigma2 Prior: nan Regularization: 0.0006
Iter: 10 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Iter: 20 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Iter: 30 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Iter: 40 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Iter: 50 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
- I trained the model on a customised dataset to create train_sequences of 50 sequences, each sequence is a d-vector embeddings sequence embedded from a 3-minute audio recording, meaning 150 minutes altogether.
- I trained with --train_iteration=1000 and -l=0.001
Even if I trained on the first 5 sequence of the train_sequences, the loss becomes nan from the first row:
Iter: 0 Training Loss: nan
Negative Log Likelihood: 20.7001 Sigma2 Prior: nan Regularization: 0.0006
Iter: 10 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Iter: 20 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Iter: 30 Training Loss: nan
Negative Log Likelihood: nan Sigma2 Prior: nan Regularization: nan
Do you know how to solve the problem?
Update: Issue solved!
My d-vector embeddings contained some zero elements, that might be the reason of nan training loss. I added all elements with an insignificant bias of 1e-6 and it's ok now
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
- [Question] Are input d-vectors for training assumed L2-normalized? HOT 8
- 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.