TDY-CNN for Text-Independent Speaker Verification

Official implementation of

• Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemetic Analysis
  by Seong-Hu Kim, Hyeonuk Nam, Yong-Hwa Park @ Human Lab, Mechanical Engineering Department, KAIST
  
  

Accepted paper in ICASSP 2022.

This code was written mainly with reference to VoxCeleb_trainer of paper 'In defence of metric learning for speaker recognition'.

Temporal Dynamic Convolutional Neural Network (TDY-CNN)

TDY-CNN efficiently applies adaptive convolution depending on time bins by changing the computation order as follows:

Requirements and versions used

Python version of 3.7.10 is used with following libraries

• pytorch == 1.8.1
• pytorchaudio == 0.8.1
• numpy == 1.19.2
• scipy == 1.5.3
• scikit-learn == 0.23.2

Dataset

We used VoxCeleb1 & 2 dataset in this paper. You can download the dataset by reffering to VoxCeleb1 and VoxCeleb1.

Training

You can train and save model in exps folder by running:

python trainSpeakerNet.py --model TDy_ResNet34_half --log_input True --encoder_type AVG --trainfunc softmaxproto --save_path exps/TDY_CNN_ResNet34 --nPerSpeaker 2 --batch_size 400

This implementation also provides accelerating training with distributed training and mixed precision training.

• Use --distributed flag to enable distributed training and --mixedprec flag to enable mixed precision training.
  • GPU indices should be set before training : os.environ['CUDA_VISIBLE_DEVICES'] ='0,1,2,3' in trainSpeakernet.py.

Results:

• This result is low-dimensional t-SNE projection of frame-level speaker embed-dings of MHRM0 and FDAS1 using (a) baseline model ResNet-34(×0.25) and (b) TDY-ResNet-34(×0.25). Left column represents embeddings for different speakers, and right column represents em-beddings for different phoneme classes.

• Embeddings by TDY-ResNet-34(×0.25) are closely gathered regardless of phoneme groups. It shows that the temporal dynamic model extracts consistent speaker information regardless of phonemes.

Pretrained models

There are pretrained models in folder pretrained_model.

For example, you can check 1.4786 of EER by running following script using TDY-ResNet-34(×0.5).

python trainSpeakerNet.py --eval --model TDy_ResNet34_half --log_input True --encoder_type AVG --trainfunc softmaxproto --save_path exps/test --eval_frames 400 --initial_model pretrained_model/pretrained_TDy_ResNet34_half.model

Citation

@article{kim2021tdycnn,
  title={Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemetic Analysis},
  author={Kim, Seong-Hu and Nam, Hyeonuk and Park, Yong-Hwa},
  journal={arXiv preprint arXiv:2110.03213},
  year={2021}
}

Please contact Seong-Hu Kim at [email protected] for any query.