Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.00755 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908429432389632 |
|---|---|
| author | Hu, Jinhai Zhang, Zhongyi Leow, Cong Sheng Goh, Wang Ling Gao, Yuan |
| author_facet | Hu, Jinhai Zhang, Zhongyi Leow, Cong Sheng Goh, Wang Ling Gao, Yuan |
| contents | This paper presents a circuit-algorithm co-design framework for learnable analog front-end (AFE) in audio signal classification. Designing AFE and backend classifiers separately is a common practice but non-ideal, as shown in this paper. Instead, this paper proposes a joint optimization of the backend classifier with the AFE's transfer function to achieve system-level optimum. More specifically, the transfer function parameters of an analog bandpass filter (BPF) bank are tuned in a signal-to-noise ratio (SNR)-aware training loop for the classifier. Using a co-design loss function LBPF, this work shows superior optimization of both the filter bank and the classifier. Implemented in open-source SKY130 130nm CMOS process, the optimized design achieved 90.5%-94.2% accuracy for 10-keyword classification task across a wide range of input signal SNR from 5 dB to 20 dB, with only 22k classifier parameters. Compared to conventional approach, the proposed audio AFE achieves 8.7% and 12.9% reduction in power and capacitor area respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00755 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LearnAFE: Circuit-Algorithm Co-design Framework for Learnable Audio Analog Front-End Hu, Jinhai Zhang, Zhongyi Leow, Cong Sheng Goh, Wang Ling Gao, Yuan Audio and Speech Processing Artificial Intelligence Sound This paper presents a circuit-algorithm co-design framework for learnable analog front-end (AFE) in audio signal classification. Designing AFE and backend classifiers separately is a common practice but non-ideal, as shown in this paper. Instead, this paper proposes a joint optimization of the backend classifier with the AFE's transfer function to achieve system-level optimum. More specifically, the transfer function parameters of an analog bandpass filter (BPF) bank are tuned in a signal-to-noise ratio (SNR)-aware training loop for the classifier. Using a co-design loss function LBPF, this work shows superior optimization of both the filter bank and the classifier. Implemented in open-source SKY130 130nm CMOS process, the optimized design achieved 90.5%-94.2% accuracy for 10-keyword classification task across a wide range of input signal SNR from 5 dB to 20 dB, with only 22k classifier parameters. Compared to conventional approach, the proposed audio AFE achieves 8.7% and 12.9% reduction in power and capacitor area respectively. |
| title | LearnAFE: Circuit-Algorithm Co-design Framework for Learnable Audio Analog Front-End |
| topic | Audio and Speech Processing Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2507.00755 |