Robotic sound-source localisation architecture using cross-correlation and recurrent neural networks

Murray, John; Erwin, Harry; Wermter, Stefan

doi:10.1016/j.neunet.2009.01.013

Cited by 40 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A good example of the use of this Pearson-based crosscorrelation method for DOA estimation in a robot audition application is presented in [24], where it provided limited results. Unfortunately, issues have arisen when using this method in reverberative and noisy environments [25], as the CCV calculations insert bias errors in such circumstances, which result in incorrect ITD estimations.…”

Section: Background On Multi-doa Estimationmentioning

confidence: 99%

Lightweight multi-DOA tracking of mobile speech sources

Rascón

Fuentes

Meza

2015

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Estimating the directions of arrival (DOAs) of multiple simultaneous mobile sound sources is an important step for various audio signal processing applications. In this contribution, we present an approach that improves upon our previous work that is now able to estimate the DOAs of multiple mobile speech sources, while being light in resources, both hardware-wise (only using three microphones) and software-wise. This approach takes advantage of the fact that simultaneous speech sources do not completely overlap each other. To evaluate the performance of this approach, a multi-DOA estimation evaluation system was developed based on a corpus collected from different acoustic scenarios named Acoustic Interactions for Robot Audition (AIRA).

show abstract

Section: Background On Multi-doa Estimationmentioning

confidence: 99%

Lightweight multi-DOA tracking of mobile speech sources

Rascón

Fuentes

Meza

2015

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

show abstract

“…A number of computational models utilizing various mathematical techniques for sound localization have been reported in the literature (Huang et al, 1999; Handzel and Krishnaprasad, 2002; Nakashima et al, 2003; Willert et al, 2006; Keyrouz and Diepold, 2008, Li et al, 2009; Murray et al, 2009). In attempting to develop more biologically inspired approaches, a number of researchers have also proposed ANN based models (Palmieri et al, 1991; Backman and Karjalainen, 1993; Datum et al, 1996; Abdel Alim and Farag, 2000; Chung et al, 2000; Hao et al, 2007; Keyrouz and Diepold, 2008).…”

Section: Models Of Sound Localizationmentioning

confidence: 99%

A spiking neural network model of the medial superior olive using spike timing dependent plasticity for sound localization

Glackin¹

2010

Front.Comput.Neurosci.

View full text Add to dashboard Cite

Sound localization can be defined as the ability to identify the position of an input sound source and is considered a powerful aspect of mammalian perception. For low frequency sounds, i.e., in the range 270 Hz–1.5 KHz, the mammalian auditory pathway achieves this by extracting the Interaural Time Difference between sound signals being received by the left and right ear. This processing is performed in a region of the brain known as the Medial Superior Olive (MSO). This paper presents a Spiking Neural Network (SNN) based model of the MSO. The network model is trained using the Spike Timing Dependent Plasticity learning rule using experimentally observed Head Related Transfer Function data in an adult domestic cat. The results presented demonstrate how the proposed SNN model is able to perform sound localization with an accuracy of 91.82% when an error tolerance of ±10° is used. For angular resolutions down to 2.5°, it will be demonstrated how software based simulations of the model incur significant computation times. The paper thus also addresses preliminary implementation on a Field Programmable Gate Array based hardware platform to accelerate system performance.

show abstract

“…It is one of the main sources of information for DOA estimation, as it provides a clear relation to the direction of the source (it was applied in [10] with limited results). The Inter-aural Intensity Difference (IID) is the difference in magnitude between both microphones and can also be used for DOA estimation, although a training stage is usually necessary for it to be useful, as it was observed in [11].…”

Section: On Source Direction Estimationmentioning

confidence: 99%

“…A sophisticated recording system may be able to overcome them, such as the one proposed in [17] that used a 24-microphone 1-D array for precision. However, a high amount of microphones may be impractical to carry by many of the currently-in-use service robots [20,11], such as our in-house robot, Golem, herein described.…”

Section: Introductionmentioning

confidence: 99%

Robotic Orientation towards Speaker for Human-Robot Interaction

Rascón

Avilés

Pineda

2010

Advances in Artificial Intelligence – IBERAMIA 2010

View full text Add to dashboard Cite

Abstract. The orientation of conversational robots to face their interlocutors is essential for natural and efficient Human-Robot Interaction (HRI). In this paper, progress towards this objective is presented: a service robot able to detect the direction of a user, and orient itself towards him/her, in a complex auditive environment, using only voice and a 3-microphone system. This functionality is integrated within Spoken HRI using dialogue models and a cognitive architecture. The paper further discusses applications where robotic orientation benefits HRI, such as a tour-guide robot capable to guide a poster session and a "Marco Polo" game where a robot aims to follow a user purely by sound.

show abstract

Robotic sound-source localisation architecture using cross-correlation and recurrent neural networks

Cited by 40 publications

References 24 publications

Lightweight multi-DOA tracking of mobile speech sources

Lightweight multi-DOA tracking of mobile speech sources

A spiking neural network model of the medial superior olive using spike timing dependent plasticity for sound localization

Robotic Orientation towards Speaker for Human-Robot Interaction

Contact Info

Product

Resources

About