TsetlinKWS: A 65nm 16.58uW, 0.63mm2 State-Driven Convolutional Tsetlin Machine-Based Accelerator For Keyword Spotting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912673945354240 |
|---|---|
| author | Lin, Baizhou Fang, Yuetong Xu, Renjing Shafik, Rishad Chauhan, Jagmohan |
| author_facet | Lin, Baizhou Fang, Yuetong Xu, Renjing Shafik, Rishad Chauhan, Jagmohan |
| contents | The Tsetlin Machine (TM) has recently attracted attention as a low-power alternative to neural networks due to its simple and interpretable inference mechanisms. However, its performance on speech-related tasks remains limited. This paper proposes TsetlinKWS, the first algorithm-hardware co-design framework for the Convolutional Tsetlin Machine (CTM) on the 12-keyword spotting task. Firstly, we introduce a novel Mel-Frequency Spectral Coefficient and Spectral Flux (MFSC-SF) feature extraction scheme together with spectral convolution, enabling the CTM to reach its first-ever competitive accuracy of 87.35% on the 12-keyword spotting task. Secondly, we develop an Optimized Grouped Block-Compressed Sparse Row (OG-BCSR) algorithm that achieves a remarkable 9.84$\times$ reduction in model size, significantly improving the storage efficiency on CTMs. Finally, we propose a state-driven architecture tailored for the CTM, which simultaneously exploits data reuse and sparsity to achieve high energy efficiency. The full system is evaluated in 65 nm process technology, consuming 16.58 $μ$W at 0.7 V with a compact 0.63 mm$^2$ core area. TsetlinKWS requires only 907k logic operations per inference, representing a 10$\times$ reduction compared to the state-of-the-art KWS accelerators, positioning the CTM as a highly-efficient candidate for ultra-low-power speech applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TsetlinKWS: A 65nm 16.58uW, 0.63mm2 State-Driven Convolutional Tsetlin Machine-Based Accelerator For Keyword Spotting Lin, Baizhou Fang, Yuetong Xu, Renjing Shafik, Rishad Chauhan, Jagmohan Sound Hardware Architecture Audio and Speech Processing B.7; C.3; I.2 The Tsetlin Machine (TM) has recently attracted attention as a low-power alternative to neural networks due to its simple and interpretable inference mechanisms. However, its performance on speech-related tasks remains limited. This paper proposes TsetlinKWS, the first algorithm-hardware co-design framework for the Convolutional Tsetlin Machine (CTM) on the 12-keyword spotting task. Firstly, we introduce a novel Mel-Frequency Spectral Coefficient and Spectral Flux (MFSC-SF) feature extraction scheme together with spectral convolution, enabling the CTM to reach its first-ever competitive accuracy of 87.35% on the 12-keyword spotting task. Secondly, we develop an Optimized Grouped Block-Compressed Sparse Row (OG-BCSR) algorithm that achieves a remarkable 9.84$\times$ reduction in model size, significantly improving the storage efficiency on CTMs. Finally, we propose a state-driven architecture tailored for the CTM, which simultaneously exploits data reuse and sparsity to achieve high energy efficiency. The full system is evaluated in 65 nm process technology, consuming 16.58 $μ$W at 0.7 V with a compact 0.63 mm$^2$ core area. TsetlinKWS requires only 907k logic operations per inference, representing a 10$\times$ reduction compared to the state-of-the-art KWS accelerators, positioning the CTM as a highly-efficient candidate for ultra-low-power speech applications. |
| title | TsetlinKWS: A 65nm 16.58uW, 0.63mm2 State-Driven Convolutional Tsetlin Machine-Based Accelerator For Keyword Spotting |
| topic | Sound Hardware Architecture Audio and Speech Processing B.7; C.3; I.2 |
| url | https://arxiv.org/abs/2510.24282 |