Loading…
Loading…
This repository provides all the necessary tools to perform speech emotion diarization with a fine-tuned wavlm (large) model using SpeechBrain.
The model is trained on concatenated audios and tested on ZaionEmotionDataset. The metric is Emotion Diarization Error Rate (EDER). For more details please check the paper link.
For a better experience, we encourage you to learn more about SpeechBrain. The model performance on ZED (test set) is:
| Release | EDER(%) |
|---|---|
| 05-07-23 | 29.7 (Avg: 30.2) |
This system is composed of a wavlm encoder a downstream frame-wise classifier. The task aims to predict the correct emotion components and their boundaries within a speech recording. For now, the model was trained with audios that contain only 1 non-neutral emotion event.
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 diarize_file if needed.
First of all, please install the development version of SpeechBrain with the following command:
git clone https://github.com/speechbrain/speechbrain.git
cd speechbrain
pip install -r requirements.txt
pip install --editable .
Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.
from speechbrain.inference.diarization import Speech_Emotion_Diarization
classifier = Speech_Emotion_Diarization.from_hparams(
source="speechbrain/emotion-diarization-wavlm-large"
)
diary = classifier.diarize_file("speechbrain/emotion-diarization-wavlm-large/example.wav")
print(diary)
# {
# 'speechbrain/emotion-diarization-wavlm-large/example.wav':
# [
# {'start': 0.0, 'end': 1.94, 'emotion': 'n'}, # n -> neutral
# {'start': 1.94, 'end': 4.48, 'emotion': 'h'} # h -> happy
# ]
# }
diary = classifier.diarize_file("speechbrain/emotion-diarization-wavlm-large/example_sad.wav")
print(diary)
# {
# 'speechbrain/emotion-diarization-wavlm-large/example_sad.wav':
# [
# {'start': 0.0, 'end': 3.54, 'emotion': 's'}, # s -> sad
# {'start': 3.54, 'end': 5.26, 'emotion': 'n'} # n -> neutral
# ]
# }
The output will contain a dictionary of emotion components and their boundaries.
To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.
The model was trained with SpeechBrain (aa018540). To train it from scratch follow these steps:
git clone https://github.com/speechbrain/speechbrain/
cd speechbrain
pip install -r requirements.txt
pip install -e .
cd recipes/ZaionEmotionDataset/emotion_diarization
python train.py hparams/train.yaml --zed_folder /path/to/ZED --emovdb_folder /path/to/EmoV-DB --esd_folder /path/to/ESD --iemocap_folder /path/to/IEMOCAP --jlcorpus_folder /path/to/JL_corpus --ravdess_folder /path/to/RAVDESS
You can find our training results (models, logs, etc) here.
The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
@article{wang2023speech,
title={Speech Emotion Diarization: Which Emotion Appears When?},
author={Wang, Yingzhi and Ravanelli, Mirco and Nfissi, Alaa and Yacoubi, Alya},
journal={arXiv preprint arXiv:2306.12991},
year={2023}
}
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}
}