metadata

language: en
thumbnail: null
tags:
  - speechbrain
  - embeddings
  - Speaker
  - Verification
  - Identification
  - pytorch
  - ECAPA
  - TDNN
license: apache-2.0
datasets:
  - voxceleb
metrics:
  - EER
widget:
  - example_title: VoxCeleb Speaker id10003
    src: https://cdn-media.huggingface.co/speech_samples/VoxCeleb1_00003.wav
  - example_title: VoxCeleb Speaker id10004
    src: https://cdn-media.huggingface.co/speech_samples/VoxCeleb_00004.wav

Speaker Verification with ECAPA-TDNN embeddings on Voxceleb

This repository provides all the necessary tools to perform speaker verification with a pretrained ECAPA-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(%)
05-03-21	0.80

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.

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.pretrained import EncoderClassifier
classifier = EncoderClassifier.from_hparams(source="speechbrain/spkrec-ecapa-voxceleb")
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="speechbrain/spkrec-ecapa-voxceleb", savedir="pretrained_models/spkrec-ecapa-voxceleb")
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.

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_ecapa_tdnn.yaml --data_folder=your_data_folder

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

Speaker Diarization with ECAPA-TDNN Embeddings

Note that, this trained ECAPA-TDNN model is used for speaker diarization task. A full diarization pipeline including boudary preparation using RTTM files, speaker embedding extraction, and backend spectral clustering for AMI dataset can be found here.

Run Inference for Diarization:

cd  recipes/AMI/Diarization
python experiment.py hparams/ecapa_tdnn.yaml

Limitations

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

Referencing ECAPA-TDNN

@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},
}

Referencing Speaker Diarization with ECAPA-TDNN

@inproceedings{dawalatabad21_interspeech,
  author={Nauman Dawalatabad and Mirco Ravanelli and François Grondin and Jenthe Thienpondt and Brecht Desplanques and Hwidong Na},
  title={{ECAPA-TDNN Embeddings for Speaker Diarization}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={3560--3564},
  doi={10.21437/Interspeech.2021-941}
}

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/