Multi-Sound-Source Localization Using Machine Learning for Small Autonomous Unmanned Vehicles with a Self-Rotating Bi-Microphone Array

Gala, Deepak; Lindsay, Nathan; Sun, Liang

doi:10.1007/s10846-021-01481-4

Cited by 8 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This would result in a higher number of coupled microphone pairs that could be integrated into the bioinspired method. In comparison, a method was developed in [17] to perform 3D sound source localization based on ITD signals of a selfrotating two-microphone array. That method also achieved a high accuracy and was successful in 3D localization of wide-band speech sources and white noise sound sources.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Direction-of-arrival estimation for acoustic signals based on direction-dependent parameter tuning of a bioinspired binaural coupling system

2023

View full text Add to dashboard Cite

Bioinspired methods for sound source localization offer opportunities for resource reduction as well as concurrent performance improvement in contrast to conventional techniques. Usually, sound source localization requires a large number of microphones arranged in irregular geometries, and thus has high resource requirements in terms of space and data processing. Motivated by biology and using digital signal processing methods, an approach that adapts the coupled hearing system of the fly Ormia ochracea with a minimally distant two-microphone array is presented. Despite its physiology, the fly is able to overcome physical limitations in localizing low-frequency sound sources. By exploiting the filtering effect of the coupling system, the direction-of-arrival (DOA) of the sound is determined with two microphones at an intermediate distance of 0,06m. For conventional beamforming algorithms, these physical limitations would result in degraded localization performance. In this work, the bioinspired coupling system is analyzed and subsequently parameterized direction-sensitive for different directions of incidence of the sound. For the parameterization, an optimization method is presented which can be adopted for excitation with plane as well as spherical sound wave propagation. Finally, the method was assessed using simulated and measured data. For 90% of the simulated scenarios, the correct direction of incidence could be determined with an accuracy of less than 1° despite the use of a minimal distant two-microphone array. The experiments with measured data also resulted in a correct determination of the direction of incidence, which qualifies the bioinspired method for practical use in digital hardware system.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The motivation is to minimize their number without losing localization performance. For this purpose, investigations with a minimum number of two microphones have already been conducted using state-of-the-art techniques such as interaural time difference (ITD) and interaural intensity difference (IID) [15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Direction-of-arrival estimation for acoustic signals based on direction-dependent parameter tuning of a bioinspired binaural coupling system

2023

View full text Add to dashboard Cite

show abstract

“…Speech interaction technology has been rapidly developed and applied in many fields, such as in smart homes [1,2], intelligent robots [3][4][5][6], and vehicle-mounted intelligent systems. Sound location technology based on microphone arrays plays an important role as its front-end processing.…”

Section: Introductionmentioning

confidence: 99%

Efficient energy-based orthogonal matching pursuit algorithm for multiple sound source localization with unknown source count

Tang

zuo

Liu

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

In this paper, we propose a compressed sensing (CS) sound source localization algorithm based on signal energy to solve the problem of stopping iteration condition of orthogonal matching pursuit reconstruction algorithm in compressed sensing. The orthogonal matching tracking algorithm needs to stop iteration according to the number of sound sources or the change of residual. Generally, the number of sound sources cannot be known in advance, and the residual often leads to unnecessary calculation. Because the sound source is sparsely distributed in space, and its energy is concentrated and higher than that of the environmental noise, the comparison of the signal energy at different positions in each iteration reconstruction signal is used to determine whether the new sound source is added in this iteration. At the same time, the block sparsity is introduced by using multiple frequency points to avoid the problem of different iteration times of different frequency points in the same frame caused by the uneven energy distribution in the signal frequency domain. Simulation and experimental results show that the proposed algorithm retains the advantages of the orthogonal matching tracking sound source localization algorithm, and can complete the iteration well. Under the premise of not knowing the number of sound sources, the maximum error between the number of iterations and the set number of sound sources is 0.31.

show abstract

“…Compared with other detection technology [5,6], SSL has a stronger anti-interference and higher concealment, thanks to its passive localization features and its flexible adoption of different microphone-array models, and algorithms for different target sound resources [7]. SSL has been widely employed in sonar [8], torpedos [9], underwater acoustic localization [10], underwater gliders [11] and other platforms [12,13]. It is worth mentioning that computer vision is the most popular method used nowadays for mobile robots to 'sense' and 'perceive' the environment and to identify its position in a GPS-denied environment.…”

Section: Introductionmentioning

confidence: 99%

“…However, when lighting conditions are poor, the sensing capability of a visual sensor is largely degraded. In this case, microphone-supporting com-puter hearing can provide valuable situational awareness [2,4,12]. As an important branch of computer hearing, SSL has been witnessed in applications ranging from intelligent video conferencing to advanced military applications.…”

Section: Introductionmentioning

confidence: 99%

A data complementary method for sound source localization based on four-element microphone array groups

Yang¹,

Xing²,

Yan³

2021

Meas. Sci. Technol.

View full text Add to dashboard Cite

Data loss or distortion has adverse effects on sound source localization (SSL) accuracy and stability. Based on the sound source azimuth estimation algorithm, this paper establishes a model of a single four-element main microphone array, and proposes a data complementary method of SSL. The calculation formula of sound source coordinates is derived from the main array. Then, the effectiveness of the proposed algorithm is verified by the study of array parameters. Besides the sound velocity and elevation angle, the array parameters also include the distance between two array elements. Array groups are established surrounding the main array on the horizontal plane, through which the localization data are collected and complementarily processed, so as to relocate the sound source. The results show that the coordinate error rate against the theoretical data is approximately 5% and the error rate of the angle is approximately 0.5%. The SSL efficiency is well guaranteed.

show abstract

Multi-Sound-Source Localization Using Machine Learning for Small Autonomous Unmanned Vehicles with a Self-Rotating Bi-Microphone Array

Cited by 8 publications

References 32 publications

Direction-of-arrival estimation for acoustic signals based on direction-dependent parameter tuning of a bioinspired binaural coupling system

Direction-of-arrival estimation for acoustic signals based on direction-dependent parameter tuning of a bioinspired binaural coupling system

Efficient energy-based orthogonal matching pursuit algorithm for multiple sound source localization with unknown source count

A data complementary method for sound source localization based on four-element microphone array groups

Contact Info

Product

Resources

About