A novel biologically inspired neural network solution for robotic 3D sound source sensing
This paper presents a novel real-time robotic binaural sound localization method based on hierarchical fuzzy artificial neural networks and a generic set of head related transfer functions. The robot is a humanoid equipped with the KEMAR artificial head and torso. Inside the ear canals two small microphones play the role of the eardrums in collecting the impinging sound waves. The neural networks are trained using synthesized sound sources placed every 5° from 0° to 255° in azimuth, and every 5° from − 45° to 80° in elevation. To improve generalization, the training data was corrupted with noise. Thanks to fuzzy logic, the method is able to interpolate at its output, locating with high accuracy sound sources at positions which were not used for training, even in presence of strong distortion. In order to achieve high localization accuracy, two different binaural cues are combined, namely the interaural intensity differences and interaural time differences. As opposed to microphone-array methods, the presented technique, uses only two microphones to localize sound sources in a real-time 3D environment.
KeywordsBinaural hearing Robotic sound localization Fuzzy neural networks Back-propagation HRTF
Unable to display preview. Download preview PDF.
- Ajdler T, Sbaiz L and Vetterli M (2005). The plenacoustic function on the circle with application to HRTF interpolation. IEEE Int Conf Acoust Speech Signal Process 5: 824–839 Google Scholar
- Blauert J (1997). An introduction to binaural technology. In: Gilkey, R and Anderson, T (eds) Binaural and spatial hearing, pp 593–609. Lawrence and Erlbaum, Hillsdale Google Scholar
- Handzel A and Krishnaprasad P (2004). Biomimetic sound-source localization. Inf Fusion (Special Issue on Robust Speech Processing) 5: 131–140 Google Scholar
- Itakura Laboratory (1999) Database of head related transfer functions. http://www.itakura.nuee.nagoya-u.ac.jp
- Jefress LA (1957). A place theory of sound localization. J Comp Physiol Psychol 61: 468–486 Google Scholar
- Keyrouz F, Diepold K (2006) A rational HRTF interpolation approach for fast synthesis of moving sound. In: IEEE digital signal processing workshop, Whyoming, pp 222–226Google Scholar
- Keyrouz F, Naous Y, Diepold K (2006a) A new method for binaural 3D localization based on HRTFs. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), Toulouse, pp 341–344Google Scholar
- Keyrouz F, Diepold K, Dewilde P (2006b) Robust 3D robotic sound localization using state–space HRTF inversion. In: IEEE international conference on robotics and biomimetics (ROBIO), China, pp 245–250Google Scholar
- Keyrouz F, Maier W, Diepold K (2007) Robust localization and separation of concurrent sound sources using self-splitting competitive learning. In: First IEEE symposium on computational intelligence in image and signal processing (CIISP), HawaiGoogle Scholar
- Minaar P, Plogsties J and Christensen F (2005). Directional resolution of head-related transfer functions required in binaural synthesis. J Audio Eng Soc 53: 919–929 Google Scholar
- Wang QH, Ivanov T and Aarabi P (2004). Acoustic robot navigation using distributed microphone arrays. Inf Fusion (Special Issue on Robust Speech Processing) 5: 131–140 Google Scholar