Improving sound event detecting in sound source localization using TDOA method
248 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.80.2022.60-70Keywords:
Sound Source Localization; TDOA; ICA.Abstract
This paper presents several research results that enhance TDOA-based sound localization accuracy with the priority of the source of interest. In which, a solution is proposed to improve the quality of audio event detection based on the correlation filter combined with signal preprocessing by the independent component analysis technique ICA. From analysis and discussions are made on that design and using Monte Carlo simulations with the data collected in a real environment, the results show the efficiency of our proposed method in TDOA-based localization.
References
[1]. Trần Công Thìn, Bùi Ngọc Mỹ, Nguyễn Huy Hoàng, Phạm Văn Hòa, ''Xây dựng giải pháp định vị nguồn âm theo nguyên lý TDOA trong điều kiện vận tốc âm thanh biến đổi'', Hội thảo Ứng dụng Công nghệ cao vào thực tiễn - 60 năm phát triển Viện KH-CN quân sự, (2020).
[2]. Lê Bá Long, Sách hướng dẫn học tập Xác suất thống kê. Hà Nội: Học viện Công nghệ Bưu chính viễn thông, (2006).
[3]. Maximo Cobos, “A Survey of Sound Source Localization Methods in Wireless Acoustic Sensor Networks”, Wireless Communications and Mobile Computing, pp. 1–24, (2017).
[4]. F.-G. Zeng, K. Nie, G. S. Stickney, Y.-Y. Kong, M. Vongphoe, A. Bhargave, C. Wei, & K. Cao. “Speech recognition with amplitude and frequency modulations”. Proceedings of the National Academy of Sciences, 102(7), pp. 2293–2298, (2005).
[5]. G. T. Wang, X. W. Liang, Y. Y. Xue, C. Li, & Q. Ding. “Algorithm Used to Detect Weak Signals Covered by Noise in PIND”. International Journal of Aerospace Engineering, 2019, pp. 1–10, (2019).
[6]. Adrián-Martínez, S. et al. “Acoustic Signal Detection Through the Cross-Correlation Method in Experiments with Different Signal to Noise Ratio and Reverberation Conditions”. In: Garcia Pineda, M., Lloret, J., Papavassiliou, S., Ruehrup, S., Westphall, C. (eds) Ad-hoc Networks and Wireless. ADHOC-NOW 2014. Lecture Notes in Computer Science(), vol 8629. Springer, Berlin, Heidelberg, (2015).
[7]. Zhang, H., McLoughlin, I., & Song, Y. “Robust sound event recognition using convolutional neural networks”. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 559-563, (2015).
[8]. Giambattista Parascandolo and Heikki Huttunen and Tuomas Virtanen. “Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life Recordings”. CoRR, abs/1604.00861, (2016).
[9]. Kay, S. Fundamentals of Statistical Signal Processing: Estimation Theory. Prentice-Hall, Inc, (1993).
[10]. Ali Mohammad-Djafari. Non Gaussianity and Non Stationarity modeled through Hidden Variables and their use in ICA and Blind Source Separation, (2007).
[11]. Hyvärinen, A., Karhunen, J., & Oja, E. Independent Component Analysis. John Wiley & Sons, Inc, (2001).
