spkrec-ecapa-cnceleb

<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe> <br/><br/>

Speaker Verification with ECAPA-TDNN on CNCeleb

This repository a pretrained ECAPA-TDNN model using SpeechBrain. The system can be used to extract speaker embeddings as well. It is trained on CNCeleb1 + CNCeleb2 training data.

The model performance on CNCeleb1-test set(Cleaned) is:

Pipeline description

This system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss. Speaker Verification is performed using cosine distance between speaker embeddings. You can find our training results (models, logs, etc) here.

Compute your speaker embeddings

import torchaudio
from speechbrain.pretrained import EncoderClassifier
classifier = EncoderClassifier.from_hparams(source="blackstone/spkrec-ecapa-cnceleb")

signal, fs = torchaudio.load('tests/samples/ASR/spk1_snt1.wav')
embeddings = classifier.encode_batch(signal)

The system is trained with recordings sampled at 16kHz (single channel). The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling classify_file if needed. Make sure your input tensor is compliant with the expected sampling rate if you use encode_batch and classify_batch.

Perform Speaker Verification

from speechbrain.pretrained import SpeakerRecognition
verification = SpeakerRecognition.from_hparams(source="blackstone/spkrec-ecapa-voxceleb", savedir="pretrained_models/spkrec-ecapa-cnceleb")
score, prediction = verification.verify_files("tests/samples/ASR/spk1_snt1.wav", "tests/samples/ASR/spk2_snt1.wav") # Different Speakers
score, prediction = verification.verify_files("tests/samples/ASR/spk1_snt1.wav", "tests/samples/ASR/spk1_snt2.wav") # Same Speaker

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.

References

@inproceedings{DBLP:conf/interspeech/DesplanquesTD20,
  author    = {Brecht Desplanques and
               Jenthe Thienpondt and
               Kris Demuynck},
  editor    = {Helen Meng and
               Bo Xu and
               Thomas Fang Zheng},
  title     = {{ECAPA-TDNN:} Emphasized Channel Attention, Propagation and Aggregation
               in {TDNN} Based Speaker Verification},
  booktitle = {Interspeech 2020},
  pages     = {3830--3834},
  publisher = {{ISCA}},
  year      = {2020},
}
@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}
}