NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912570047201280 |
|---|---|
| author | Xian, Huhong Liu, Rui Sisman, Berrak Li, Haizhou |
| author_facet | Xian, Huhong Liu, Rui Sisman, Berrak Li, Haizhou |
| contents | Different from traditional sentence-level audio deepfake detection (ADD), partial audio deepfake detection (PADD) requires frame-level positioning of the location of fake speech. While some progress has been made in this area, leveraging semantic information from audio, especially named entities, remains an underexplored aspect. To this end, we propose NE-PADD, a novel method for Partial Audio Deepfake Detection (PADD) that leverages named entity knowledge through two parallel branches: Speech Name Entity Recognition (SpeechNER) and PADD. The approach incorporates two attention aggregation mechanisms: Attention Fusion (AF) for combining attention weights and Attention Transfer (AT) for guiding PADD with named entity semantics using an auxiliary loss. Built on the PartialSpoof-NER dataset, experiments show our method outperforms existing baselines, proving the effectiveness of integrating named entity knowledge in PADD. The code is available at https://github.com/AI-S2-Lab/NE-PADD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03829 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation Xian, Huhong Liu, Rui Sisman, Berrak Li, Haizhou Computation and Language Different from traditional sentence-level audio deepfake detection (ADD), partial audio deepfake detection (PADD) requires frame-level positioning of the location of fake speech. While some progress has been made in this area, leveraging semantic information from audio, especially named entities, remains an underexplored aspect. To this end, we propose NE-PADD, a novel method for Partial Audio Deepfake Detection (PADD) that leverages named entity knowledge through two parallel branches: Speech Name Entity Recognition (SpeechNER) and PADD. The approach incorporates two attention aggregation mechanisms: Attention Fusion (AF) for combining attention weights and Attention Transfer (AT) for guiding PADD with named entity semantics using an auxiliary loss. Built on the PartialSpoof-NER dataset, experiments show our method outperforms existing baselines, proving the effectiveness of integrating named entity knowledge in PADD. The code is available at https://github.com/AI-S2-Lab/NE-PADD. |
| title | NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.03829 |