Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910594348613632 |
|---|---|
| author | Truong, Duc-Tuan Tao, Ruijie Nguyen, Tuan Luong, Hieu-Thi Lee, Kong Aik Chng, Eng Siong |
| author_facet | Truong, Duc-Tuan Tao, Ruijie Nguyen, Tuan Luong, Hieu-Thi Lee, Kong Aik Chng, Eng Siong |
| contents | Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head self-attention (MHSA) in the Transformer model, which learns the temporal relationship of each input token. However, artifacts of synthetic speech can be located in specific regions of both frequency channels and temporal segments, while MHSA neglects this temporal-channel dependency of the input sequence. In this work, we proposed a Temporal-Channel Modeling (TCM) module to enhance MHSA's capability for capturing temporal-channel dependencies. Experimental results on the ASVspoof 2021 show that with only 0.03M additional parameters, the TCM module can outperform the state-of-the-art system by 9.25% in EER. Further ablation study reveals that utilizing both temporal and channel information yields the most improvement for detecting synthetic speech. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17376 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection Truong, Duc-Tuan Tao, Ruijie Nguyen, Tuan Luong, Hieu-Thi Lee, Kong Aik Chng, Eng Siong Sound Artificial Intelligence Audio and Speech Processing Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head self-attention (MHSA) in the Transformer model, which learns the temporal relationship of each input token. However, artifacts of synthetic speech can be located in specific regions of both frequency channels and temporal segments, while MHSA neglects this temporal-channel dependency of the input sequence. In this work, we proposed a Temporal-Channel Modeling (TCM) module to enhance MHSA's capability for capturing temporal-channel dependencies. Experimental results on the ASVspoof 2021 show that with only 0.03M additional parameters, the TCM module can outperform the state-of-the-art system by 9.25% in EER. Further ablation study reveals that utilizing both temporal and channel information yields the most improvement for detecting synthetic speech. |
| title | Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.17376 |