Presentation | 2007-03-16 The pitch invariant sound source localization system using pulsed neural networks Hirotaka OKUI, Kaname IWASA, Mauricio KUGLER, Susumu KUROYANAGI, Akira IWATA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, a sound source localization system using pulsed neural networks had been proposed. This system, based on a SOM algorithm, can successfully identify several kinds of sound sources. However, when the sound pitch is different from the training data, the system becomes unable to identify the source correctly. This problem can be solved by training the system with all pitches required for recognition. However, the required amount of memory and computational complexity make this approach unpractical. For a determined sound source, when the pitch changes, only the fundamental frequency changes, but the harmonic overtone components' relation remains the same. In this paper, we propose an extension of the present system that considers the harmonic overtone information when identifying a sound source. The performance of the proposed system is compared with the previous model by several experiments. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Pulsed Neuron Model / Self Organizing Map / Competition Learning / fundamental frequency |
Paper # | NC2006-206 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2007/3/9(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | The pitch invariant sound source localization system using pulsed neural networks |
Sub Title (in English) | |
Keyword(1) | Pulsed Neuron Model |
Keyword(2) | Self Organizing Map |
Keyword(3) | Competition Learning |
Keyword(4) | fundamental frequency |
1st Author's Name | Hirotaka OKUI |
1st Author's Affiliation | Department of Computer Science & Engineering, Nagoya Institute of Technology() |
2nd Author's Name | Kaname IWASA |
2nd Author's Affiliation | Department of Computer Science & Engineering, Nagoya Institute of Technology |
3rd Author's Name | Mauricio KUGLER |
3rd Author's Affiliation | Department of Computer Science & Engineering, Nagoya Institute of Technology |
4th Author's Name | Susumu KUROYANAGI |
4th Author's Affiliation | Department of Computer Science & Engineering, Nagoya Institute of Technology |
5th Author's Name | Akira IWATA |
5th Author's Affiliation | Department of Computer Science & Engineering, Nagoya Institute of Technology |
Date | 2007-03-16 |
Paper # | NC2006-206 |
Volume (vol) | vol.106 |
Number (no) | 590 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |