sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks
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_ | 1866909133462044672 |
|---|---|
| author | Yang, Qu Liu, Qianhui Li, Nan Ge, Meng Song, Zeyang Li, Haizhou |
| author_facet | Yang, Qu Liu, Qianhui Li, Nan Ge, Meng Song, Zeyang Li, Haizhou |
| contents | Speech applications are expected to be low-power and robust under noisy conditions. An effective Voice Activity Detection (VAD) front-end lowers the computational need. Spiking Neural Networks (SNNs) are known to be biologically plausible and power-efficient. However, SNN-based VADs have yet to achieve noise robustness and often require large models for high performance. This paper introduces a novel SNN-based VAD model, referred to as sVAD, which features an auditory encoder with an SNN-based attention mechanism. Particularly, it provides effective auditory feature representation through SincNet and 1D convolution, and improves noise robustness with attention mechanisms. The classifier utilizes Spiking Recurrent Neural Networks (sRNN) to exploit temporal speech information. Experimental results demonstrate that our sVAD achieves remarkable noise robustness and meanwhile maintains low power consumption and a small footprint, making it a promising solution for real-world VAD applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05772 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks Yang, Qu Liu, Qianhui Li, Nan Ge, Meng Song, Zeyang Li, Haizhou Sound Neural and Evolutionary Computing Audio and Speech Processing Speech applications are expected to be low-power and robust under noisy conditions. An effective Voice Activity Detection (VAD) front-end lowers the computational need. Spiking Neural Networks (SNNs) are known to be biologically plausible and power-efficient. However, SNN-based VADs have yet to achieve noise robustness and often require large models for high performance. This paper introduces a novel SNN-based VAD model, referred to as sVAD, which features an auditory encoder with an SNN-based attention mechanism. Particularly, it provides effective auditory feature representation through SincNet and 1D convolution, and improves noise robustness with attention mechanisms. The classifier utilizes Spiking Recurrent Neural Networks (sRNN) to exploit temporal speech information. Experimental results demonstrate that our sVAD achieves remarkable noise robustness and meanwhile maintains low power consumption and a small footprint, making it a promising solution for real-world VAD applications. |
| title | sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks |
| topic | Sound Neural and Evolutionary Computing Audio and Speech Processing |
| url | https://arxiv.org/abs/2403.05772 |