A Geometrical–Statistical Approach to Outlier Removal for TDOA Measurements

Compagnoni, Marco Antônio; Pini, Alessia; Canclini, Antonio; Bestagini, Paolo; Antonacci, Fabio; Tubaro, Stefano; Sarti, Augusto

doi:10.1109/tsp.2017.2701311

Cited by 53 publications

(30 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the classical literature review on this topic, these approaches can be broadly divided into three categories [ 26 , 27 ]: time delay based, beamforming based, and high-resolution spectral estimation based methods. This taxonomy relies on the fact that ASL has traditionally been considered a signal processing problem based on the definition of a signal propagation model [ 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ], but, more recently, the range of proposals in the literature has also considered strategies based on exploiting the optimization techniques and mathematical properties of related measurements [ 35 , 36 , 37 , 38 , 39 ], and also the use of machine learning strategies [ 40 , 41 , 42 ], aimed at obtaining direct mapping from specific features to source locations [ 43 ], an area in which deep learning approaches are starting to be applied and that will be further described later in this section.…”

Section: State Of the Artmentioning

confidence: 99%

Towards End-to-End Acoustic Localization Using Deep Learning: From Audio Signals to Source Position Coordinates

Vera-Diaz

Pizarro

Macías-Guarasa

2018

Sensors

100

View full text Add to dashboard Cite

This paper presents a novel approach for indoor acoustic source localization using microphone arrays, based on a Convolutional Neural Network (CNN). In the proposed solution, the CNN is designed to directly estimate the three-dimensional position of a single acoustic source using the raw audio signal as the input information and avoiding the use of hand-crafted audio features. Given the limited amount of available localization data, we propose, in this paper, a training strategy based on two steps. We first train our network using semi-synthetic data generated from close talk speech recordings. We simulate the time delays and distortion suffered in the signal that propagate from the source to the array of microphones. We then fine tune this network using a small amount of real data. Our experimental results, evaluated on a publicly available dataset recorded in a real room, show that this approach is able to produce networks that significantly improve existing localization methods based on SRP-PHAT strategies and also those presented in very recent proposals based on Convolutional Recurrent Neural Networks (CRNN). In addition, our experiments show that the performance of our CNN method does not show a relevant dependency on the speaker’s gender, nor on the size of the signal window being used.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Towards End-to-End Acoustic Localization Using Deep Learning: From Audio Signals to Source Position Coordinates

Vera-Diaz

Pizarro

Macías-Guarasa

2018

Sensors

100

View full text Add to dashboard Cite

show abstract

“…According to the classical literature review in this topic, these approaches can be broadly divided in three categories [11,12]: time delay based, beamforming based, and high-resolution spectral-estimation based methods. This taxonomy relies in the fact that ASL has been traditionally considered a signal processing problem based on the definition of a signal propagation model [11][12][13][14][15][16][17][18][19], but, more recently, the range of proposals in the literature also considered strategies based on exploiting optimization techniques and mathematical properties of related measurements [20][21][22][23][24], and also using machine learning strategies [25][26][27], aimed at obtaining a direct mapping from specific features to source locations [28], area in which deep learning approaches are starting to be applied and that will be further described later in this section.…”

Section: State Of the Artmentioning

confidence: 99%

Towards End-to-End Acoustic Localization Using Deep Learning: From Audio Signal to Source Position Coordinates

Vera-Diaz¹,

Pizarro²,

Macías-Guarasa³

2018

Preprint

View full text Add to dashboard Cite

This paper presents a novel approach for indoor acoustic source localization using microphone arrays and based on a Convolutional Neural Network (CNN). The proposed solution is, to the best of our knowledge, the first published work in which the CNN is designed to directly estimate the three dimensional position of an acoustic source, using the raw audio signal as the input information avoiding the use of hand crafted audio features. Given the limited amount of available localization data, we propose in this paper a training strategy based on two steps. We first train our network using semi-synthetic data, generated from close talk speech recordings, and where we simulate the time delays and distortion suffered in the signal that propagates from the source to the array of microphones. We then fine tune this network using a small amount of real data. Our experimental results show that this strategy is able to produce networks that significantly improve existing localization methods based on SRP-PHAT strategies. In addition, our experiments show that our CNN method exhibits better resistance against varying gender of the speaker and different window sizes compared with the other methods.

show abstract

“…, , observed by each array with additive noise 푖 , which is a realization of zero-mean white noise drawn from a normal distribution with standard deviation 휃 . Note that, in this case, the measurements are by definition free of outliers, since the deviation from the nominal DOA values is only due to the additive error model [22]. In order to enforce the statistical validity of the analysis of the cost function, we took care of two aspects.…”

Section: Test 1: Robustness Against Additive Noise On Doasmentioning

confidence: 99%

Distributed 3D Source Localization from 2D DOA Measurements Using Multiple Linear Arrays

Canclini

Antonacci

Sarti

et al. 2017

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

This manuscript addresses the problem of 3D source localization from direction of arrivals (DOAs) in wireless acoustic sensor networks. In this context, multiple sensors measure the DOA of the source, and a central node combines the measurements to yield the source location estimate. Traditional approaches require 3D DOA measurements; that is, each sensor estimates the azimuth and elevation of the source by means of a microphone array, typically in a planar or spherical configuration. The proposed methodology aims at reducing the hardware and computational costs by combining measurements related to 2D DOAs estimated from linear arrays arbitrarily displaced in the 3D space. Each sensor measures the DOA in the plane containing the array and the source. Measurements are then translated into an equivalent planar geometry, in which a set of coplanar equivalent arrays observe the source preserving the original DOAs. This formulation is exploited to define a cost function, whose minimization leads to the source location estimation. An extensive simulation campaign validates the proposed approach and compares its accuracy with state-of-the-art methodologies.

show abstract

A Geometrical–Statistical Approach to Outlier Removal for TDOA Measurements

Cited by 53 publications

References 34 publications

Towards End-to-End Acoustic Localization Using Deep Learning: From Audio Signals to Source Position Coordinates

Towards End-to-End Acoustic Localization Using Deep Learning: From Audio Signals to Source Position Coordinates

Towards End-to-End Acoustic Localization Using Deep Learning: From Audio Signal to Source Position Coordinates

Distributed 3D Source Localization from 2D DOA Measurements Using Multiple Linear Arrays

Contact Info

Product

Resources

About