Speaker Verification with ResNet embeddings on Voxceleb

This repository provides all the necessary tools to perform speaker verification with a pretrained ResNet TDNN model using SpeechBrain. The system can be used to extract speaker embeddings as well. It is trained on Voxceleb 1 + Voxceleb2 training data.

For a better experience, we encourage you to learn more about SpeechBrain. The model performance on Voxceleb1-test set(Cleaned) is:

Release	EER(%)	minDCF
29-07-23	1.05	0.1082

Pipeline description

This system is composed of an ResNet TDNN model. The system is trained with Additive Margin Softmax Loss. Speaker Verification is performed using cosine distance between speaker embeddings.

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

pip install speechbrain

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

Compute your speaker embeddings

import torchaudio
from speechbrain.inference.speaker import EncoderClassifier
classifier = EncoderClassifier.from_hparams(source="speechbrain/spkrec-resnet-voxceleb")
signal, fs =torchaudio.load('example.wav')
embeddings = classifier.encode_batch(signal)

Perform Speaker Verification

from speechbrain.inference.speaker import SpeakerRecognition
verification = SpeakerRecognition.from_hparams(source="speechbrain/spkrec-resnet-voxceleb", savedir="pretrained_models/spkrec-resnet-voxceleb")
score, prediction = verification.verify_files("speechbrain/spkrec-resnet-voxceleb/example1.wav", "speechbrain/spkrec-resnet-voxceleb/example2.flac")

The prediction is 1 if the two signals in input are from the same speaker and 0 otherwise.

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

Training

The model was trained with SpeechBrain (aa018540). To train it from scratch follows these steps:

Clone SpeechBrain:

git clone https://github.com/speechbrain/speechbrain/

Install it:

cd speechbrain
pip install -r requirements.txt
pip install -e .

Run Training:

cd  recipes/VoxCeleb/SpeakerRec
python train_speaker_embeddings.py hparams/train_resnet.yaml --data_folder=your_data_folder

You can find our training results (models, logs, etc) here.

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

Referencing ResNet TDNN

@article{VILLALBA2020101026,
title = {State-of-the-art speaker recognition with neural network embeddings in NIST SRE18 and Speakers in the Wild evaluations},
journal = {Computer Speech & Language},
volume = {60},
pages = {101026},
year = {2020},
doi = {https://doi.org/10.1016/j.csl.2019.101026},
author = {Jesús Villalba and Nanxin Chen and David Snyder and Daniel Garcia-Romero and Alan McCree and Gregory Sell and Jonas Borgstrom and Leibny Paola García-Perera and Fred Richardson and Réda Dehak and Pedro A. Torres-Carrasquillo and Najim Dehak},
}

Citing SpeechBrain

Please, cite SpeechBrain if you use it for your research or business.

@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}

About SpeechBrain

Website: https://speechbrain.github.io/
Code: https://github.com/speechbrain/speechbrain/
HuggingFace: https://huggingface.co/speechbrain/