UMUTeam/w2v-bert-emotion-en is an English speech emotion recognition model developed as part of speech-emotion, an open-source multilingual and multimodal toolkit for emotion recognition from speech, text, and multimodal inputs.

This model performs emotion classification directly from English speech audio.

The model is based on the Wav2Vec2-BERT architecture and was fine-tuned for speech emotion recognition tasks in English.

It is designed to operate as a standalone speech-only emotion recognition system or as part of the broader speech-emotion framework, where acoustic representations can be combined with textual representations for multimodal emotion recognition.

The model predicts one of the following emotion labels:

angry
disgust
fear
happy
neutral
sad
surprise

Intended use

This model is intended for research and applied scenarios involving English speech emotion recognition, such as:

emotion analysis from speech recordings
conversational speech analysis
affective computing research
human-computer interaction
emotion-aware conversational agents
integration into multimodal emotion recognition pipelines

It can be used directly with the Hugging Face transformers library or through the speech-emotion toolkit.

Out-of-scope use

This model should not be used as the sole basis for high-stakes decisions, including but not limited to:

clinical diagnosis
mental health assessment
employment, legal, or educational decisions
biometric profiling or surveillance
automated decisions affecting individuals without human oversight

Emotion recognition is inherently uncertain and context-dependent. Predictions should be interpreted as model estimates, not as definitive assessments of a person's emotional state.

Training data

The model was trained on the English speech datasets used in the speech-emotion project.

The training data combines multiple publicly available English speech emotion recognition datasets, including:

RAVDESS
TESS
datasets derived from prior speech emotion recognition research benchmarks

Because the original datasets use different emotion taxonomies, all datasets were harmonized into a unified seven-class emotion taxonomy:

angry
disgust
fear
happy
neutral
sad
surprise

For the English speech emotion recognition setup:

Training samples: 3,622
Validation samples: 453
Test samples: 453

More details about the dataset preprocessing and label harmonization pipeline are available in the project repository:

https://github.com/NLP-UMUTeam/umuteam-speech-emotion

Evaluation

The model was evaluated on the English held-out test set used in the speech-emotion toolkit.

Performance comparison on English emotion recognition

Configuration	Accuracy	Weighted Precision	Weighted F1	Macro F1
Speech-only	95.1435	95.2700	95.1575	95.1679
Text-only	76.0842	75.5723	75.6852	68.0266
Multimodal (Concat)	96.0462	96.0880	96.0257	96.0462
Multimodal (Mean)	90.2870	90.5162	90.2334	90.2589
Multimodal (Multihead)	93.1567	93.2715	93.1898	93.2115

These results show that speech-based emotion recognition provides strong performance for English emotion analysis, while multimodal approaches combining speech and text achieve even higher robustness and overall performance.

How to use

python

from transformers import pipeline

classifier = pipeline(
    "audio-classification",
    model="UMUTeam/w2v-bert-emotion-en"
)

prediction = classifier("audio.wav")

print(prediction)

You can also use this model through the speech-emotion toolkit:

pip install speech-emotion

python

from speech_emotion import predict_emotion

emotion = predict_emotion(
    audio_path="audio.wav",
    language="en",
    mode="audio",
    model_config_path="model.json"
)

print("Detected emotion:", emotion)

Repository:

https://github.com/NLP-UMUTeam/umuteam-speech-emotion

Limitations

The model is designed for English speech and may not perform reliably on other languages.
It predicts a single label from a fixed set of seven emotions.
Emotion expression is subjective and highly context-dependent.
Performance may decrease with noisy audio, overlapping speakers, low-quality recordings, strong accents, or domain shifts.
Speech-only emotion recognition may miss relevant contextual or visual information that could improve emotion interpretation.

Bias and ethical considerations

Emotion recognition systems may reflect biases present in their training data, including differences related to accents, speaking styles, demographics, recording conditions, or annotation subjectivity.

Users should avoid interpreting predictions as objective truths about a person's internal emotional state. The model should be used with transparency, appropriate consent, and human oversight, especially in sensitive contexts.

Citation

If you use this model in your research, please cite the following works:

speech-emotion toolkit

bibtex

@article{PAN2026102677,
title = {speech-emotion: A multilingual and multimodal toolkit for emotion recognition from speech},
journal = {SoftwareX},
volume = {34},
pages = {102677},
year = {2026},
issn = {2352-7110},
doi = {https://doi.org/10.1016/j.softx.2026.102677},
url = {https://www.sciencedirect.com/science/article/pii/S235271102600169X},
author = {Ronghao Pan and Tomás Bernal-Beltrán and José Antonio García-Díaz and Rafael Valencia-García},
}

Acknowledgments

This work is part of the research project LaTe4PoliticES (PID2022-138099OB-I00), funded by MICIU/AEI/10.13039/501100011033 and the European Regional Development Fund (ERDF/EU - FEDER/UE), “A way of making Europe”.

Mr. Tomás Bernal-Beltrán is supported by the University of Murcia through the predoctoral programme.