A Convolution-Neural-Network Feedforward Active-Noise-Cancellation System on FPGA for In-Ear Headphone
Source abstract
Abstract
A real-time streaming feedforward active-noise-cancellation (ANC) system for an in-ear headphone was demonstrated in a real application scenario, by implementing a 10-layer dilated convolutional-neural-network (CNN) on a field programmable gate array (FPGA). A 16 × 16 systolic array was used in the FPGA, to speed up the model computation. The system latency was 170.6 μs, at the system clock frequency of 120 MHz. The CNN model used 3232 parameters. Due to the large input receptive field, of 327 ms, this work achieved total power reduction, of 14.8 dB and 14.3 dB at the noise incident direction of 0∘ and 90∘, respectively, and the noise attenuation bandwidth was 2000 Hz at both angles; all results were superior to those of the conventional FxLMS algorithm.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Adaptive Filtering Techniques · Speech and Audio Processing · Hearing Loss and Rehabilitation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, Pohang University of Science and Technology (POSTECH), Pohang 37673, Korea
Funding
Samsung Electronics Co., Ltd · Ministry of Education
References (26)
Show source-provided references
1. Active Noise Control: A Tutorial Review10.1109/5.763310 ↗
2. Kuo, S.M., and Morgan, D.R. (1996). Active Noise Control Systems: Algorithms and DSP implementations, John Wiley & Sons.
3. Elliott, S.J. (2001). Signal Processing of Active Noise Control, Academic Press.
4. Miljković, D. (June, January 30). Active noise control: From analog to digital-Last 80 years. Proceedings of the 2016 39th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia.10.1109/MIPRO.2016.7522313 ↗
5. Recent advances on active noise control: Open issues and innovative applications10.1017/ATSIP.2012.4 ↗
6. An integrated audio and active noise control headset10.1109/TCE.2002.1010128 ↗
7. Adaptive feedback active noise control headset: Implementation, evaluation and its extensions10.1109/TCE.2005.1510511 ↗
8. A robust hybrid feedback active noise cancellation headset10.1109/TSA.2005.848878 ↗
9. Integrated automotive signal processing and audio system10.1109/30.234630 ↗
10. Active Noise Control System for Headphone Applications10.1109/TCST.2005.863667 ↗
11. Active Noise Control in Headsets by using a Low-Cost Microcontroller10.1109/TIE.2010.2058071 ↗
12. Vu, H.-S., and Chen, K.-H. (2016, January 25–27). A 1.4 mW low-power feedback FxLMS ANC VLSI design for in-ear Headphones. Proceedings of the 2016 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), Hsinchu, Taiwan.10.1109/VLSI-DAT.2016.7482543 ↗
13. Kuo, S.M., Chen, Y.-R., Chang, C.-Y., and Lai, C.-W. (2018). Development and Evaluation of Light-Weight Active Noise Cancellation Earphones. Appl. Sci., 8.10.3390/app8071178 ↗
14. Listening in a Noisy Environment: Integration of active noise control in audio products10.1109/MCE.2016.2590159 ↗
15. A Low-Power Broad-Bandwidth Noise Cancellation VLSI Circuit Design for In-Ear Headphones10.1109/TVLSI.2015.2480425 ↗
16. Vu, H.-S., Chen, K.-H., Sun, S.-F., Fong, T.-M., Hsu, C.-W., and Wang, L. (2015, January 27–29). A Power-Efficient Circuit Design of Feed-Forward FxLMS Active Noise Cancellation for In-ear Headphones. Proceedings of the 2015 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), Hsinchu, Taiwan.10.1109/VLSI-DAT.2015.7114524 ↗
17. Vu, H.-S., Chen, K.-H., Sun, S.-F., Fong, T.-M., Hsu, C.-W., and Wang, L. (2015, January 24–27). A 6.42 mW low-power feedforward FxLMS ANC VLSI design for in-ear headphones. Proceedings of the 2015 IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal.10.1109/ISCAS.2015.7169214 ↗
18. Vu, H.-S., Chen, K.-H., and Fong, T.-M. (2015, January 6–8). Active noise control for in-ear headphones: Implementation and evaluation. Proceedings of the 2015 International Conference on Consumer Electronics-Taiwan, Taipei, Taiwan.10.1109/ICCE-TW.2015.7216889 ↗
19. Huang, C.-R., Chang, C.-Y., and Kuo, S.M. (2021, January 26–28). Directional Dependency for Feedforward Active Noise Control Systems with In-Ear Headphones. Proceedings of the 2021 International Conference on System Science and Engineering(ICSSE), Ho Chi Minh City, Vietnam.10.1109/ICSSE52999.2021.9537943 ↗
20. Shi, D., Shi, C., and Gan, W.-S. (2016, January 13–16). A Systolic FxLMS Structure for Implementation of Feedforward Active Noise Control on FPGA. Proceedings of the 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Jeju, Korea.10.1109/APSIPA.2016.7820755 ↗
21. Causality study on a feedforward active noise control headset with different noise coming directions in free field10.1016/j.apacoust.2014.01.004 ↗
22. Study of causality constraint on feedforward active noise control systems10.1109/82.752950 ↗
23. Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). Wavenet: A Generative Model for Raw Audio. arXiv.
24. Schreier, R., and Temes, G.C. (2017). Understanding Delta-Sigma Data Converters, Wiley-IEEE Press.10.1002/9781119258308 ↗
25. Feedforward Selective Fixed-Filter Active Noise Control: Algorithm and Implementation
26. Selective fixed-filter active noise control based on convolutional neural network10.1016/j.sigpro.2021.108317 ↗