language: en
thumbnail: null
tags:
- embeddings
- Sound
- Keywords
- Keyword Spotting
- pytorch
- ECAPA-TDNN
- TDNN
- Command Recognition
license: apache-2.0
datasets:
- Urbansound8k
metrics:
- Accuracy
Command Recognition with ECAPA embeddings on UrbanSoudnd8k
This repository provides all the necessary tools to perform sound recognition with SpeechBrain using a model pretrained on UrbanSound8k. You can download the dataset here The provided system can recognize the following 10 keywords:
dog_bark, children_playing, air_conditioner, street_music, gun_shot, siren, engine_idling, jackhammer, drilling, car_horn
For a better experience, we encourage you to learn more about SpeechBrain. The given model performance on the test set is:
| Release | Accuracy 1-fold (%) |
|---|---|
| 04-06-21 | 75.5 |
Pipeline description
This system is composed of a ECAPA model coupled with statistical pooling. A classifier, trained with Categorical Cross-Entropy Loss, is applied on top of that.
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.
Perform Sound Recognition
import torchaudio
from speechbrain.pretrained import EncoderClassifier
classifier = EncoderClassifier.from_hparams(source="speechbrain/urbansound8k_ecapa", savedir="pretrained_models/gurbansound8k_ecapa")
out_prob, score, index, text_lab = classifier.classify_file('speechbrain/urbansound8k_ecapa/dog_bark.wav')
print(text_lab)
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 (8cab8b0c). 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/UrbanSound8k/SoundClassification
python train.py hparams/train_ecapa_tdnn.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 ECAPA
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 UrbanSound
Author = {Salamon, J. and Jacoby, C. and Bello, J. P.},
Booktitle = {22nd {ACM} International Conference on Multimedia (ACM-MM'14)},
Month = {Nov.},
Pages = {1041--1044},
Title = {A Dataset and Taxonomy for Urban Sound Research},
Year = {2014}}
Referencing SpeechBrain
@misc{SB2021,
author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
title = {SpeechBrain},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
}
About SpeechBrain
SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains.
Website: https://speechbrain.github.io/