|
naistar (NAIST Academic Repository) >
学術リポジトリ naistar / NAIST Academic Repository naistar >
国際会議発表論文 / Proceedings >
情報科学研究科 / Graduate School of Information Science >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10061/8211
|
| Title: | Performance improvement of higher-order ICA using lerning period detection based on closed-form second-order ICA and kurtosis |
| Authors: | Yuuki Fujihara
Yu Takahashi
Shigeki Miyabe
Hiroshi Saruwatari
Kiyohiro Shikano
Akira Tanaka |
| Keywords: | Independent component analysis
blind source separation
voice activity detection
closed-form solution |
| Issue Date: | Sep-2008 |
| Article Number: | 9077 |
| Abstract: | A hands-free system with conventional independent component analysis (ICA) should update the separation filter constantly to follow the hourly environment change. However, when the separation-filter is updated in the period where the user absent, ICA often yields an undesired separation filter. In this paper, we propose a novel algorithm of kurtosis-based voice activity detection (VAD) for an appropriate ICA optimization. In this algorithm, first, closed-form 2nd-order ICA (SO-ICA) is performed for providing the roughly separated signals, and based on the kurtosis of their signals, VAD is processed. Next, when the current time period is voiced block, the higher-order ICA's re-optimization is applied using the previously obtained SO-ICA's solution as the initial filter; this results in a fast and high convergence. The effectiveness of the proposed method is shown in a simulation experiment for blind spatial subtraction array with the proposed method. |
| Description: | IWAENC2008: the 11th International Workshop on Acoustic Echo and Noise Control, September 14-17, 2008, Seattle, Washington USA. |
| URI: | http://hdl.handle.net/10061/8211 |
| Text Version: | Publisher |
| Appears in Collections: | 情報科学研究科 / Graduate School of Information Science
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
