Napredna pretraga

Pregled bibliografske jedinice broj: 635935

Active Speaker Localization with Circular Likelihoods and Bootstrap Filtering


Marković, Ivan; Portello, Alban; Danès, Patrick; Petrović, Ivan; Argentieri, Sylvain
Active Speaker Localization with Circular Likelihoods and Bootstrap Filtering // Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), Invited Session on Robot Audition
Tokio, Japan, 2013. str. 2914-2920 (pozvano predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Active Speaker Localization with Circular Likelihoods and Bootstrap Filtering

Autori
Marković, Ivan ; Portello, Alban ; Danès, Patrick ; Petrović, Ivan ; Argentieri, Sylvain

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), Invited Session on Robot Audition / - Tokio, Japan, 2013, 2914-2920

ISBN
978-1-4673-6357-0

Skup
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), Invited Session on Robot Audition

Mjesto i datum
Tokio, Japan, 03-07.11.2013.

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Active Speaker Localization; Binaural Hearing; Circular Likelihood; Boostrap Filtering

Sažetak
This paper deals with speaker localization in two dimensions from a mobile binaural head. A bootstrap particle filtering scheme is used to perform active localization, i.e. to infer source location by fusing the binaural perception with the sensor motor commands. It relies on an original pseudo-likelihood of the source azimuth which captures both the inter- aural level and phase differences. Since the pseudo-likelihood is discrete, it is fitted with a mixture of circular distributions in order to enhance its resolution. For the fitting task two mixtures are compared and evaluated, namely the mixture of von Mises and wrapped Cauchy distributions. Furthermore, a solution is presented for calculating the von Mises curvefitting with low uncertainty, since the direct implementation can quickly surpass double precision floating number representation. The performance of the filter is compared using both the raw and fitted pseudo-likelihoods on experiments recorded in an acoustically prepared room with ground-truth obtained from a motion capture system. The results show that the proposed algorithm successfully localizes the speaker with an advantage in the direction of the fitted von Mises mixture likelihood.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti



POVEZANOST RADA


Projekt / tema
036-0363078-3018 - Upravljanje mobilnim robotima i vozilima u nepoznatim i dinamičkim okruženjima (Ivan Petrović, )
ACROSS

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb