SENSE-2ATTR

SENSE-2ATTR is a unified speech encoder that jointly learns multiple utterance-level attribute representations from a single speech signal.

This version models two attributes:

  • Semantic representation: 1024 dimensions
  • Speaker representation: 192 dimensions
Attribute Teacher model Dimension
Semantic BGE-M3 1024
Speaker ECAPA-TDNN 192

Installation

pip install speechbrain

Usage

from speechbrain.inference.interfaces import foreign_class

model = foreign_class(
    source="LIA-AvignonUniversity/SENSE-2ATTR",
    pymodule_file="custom.py",
    classname="SENSEEncoder",
    run_opts={"device": "cuda:0"},
)

Extract the representations from an audio file:

outputs = model.encode_file("example.wav")

semantic_embedding = outputs["sem"]
# torch.Size([1, 1024])
speaker_embedding = outputs["spkr"]
# torch.Size([1, 192])

Paper

Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder

Maryem Bouziane, Salima Mdhaffar, Yannick Estève

https://arxiv.org/abs/2603.08312

Citation

If you use this model, please cite:

@misc{bouziane2026learning,
  title={Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder},
  author={Maryem Bouziane and Salima Mdhaffar and Yannick Est{\`e}ve},
  year={2026},
  eprint={2603.08312},
  archivePrefix={arXiv}
}

Authors

  • Maryem Bouziane
  • Salima Mdhaffar
  • Yannick Estève

Laboratoire Informatique d'Avignon (LIA)
Avignon Université, France

Downloads last month
2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for LIA-AvignonUniversity/SENSE-2ATTR