Robust voice activity detection based on noise eigenspace
-
- Ying Dongwen
- School of Information Science, Japan Advanced Institute of Science and Technology
-
- Shi Yu
- Microsoft Research Asia
-
- Lu Xugang
- School of Information Science, Japan Advanced Institute of Science and Technology
-
- Dang Jianwu
- School of Information Science, Japan Advanced Institute of Science and Technology
-
- Soong Frank
- Microsoft Research Asia
この論文をさがす
抄録
In this study, we propose a voice activity detector (VAD) based on a noise eigenspace, which improve the robustness of VAD by utilizing the compression capability of the eigenspace. A noise eigenspace is constructed by using eigenvalue decomposition of the noise correlation matrix. When noisy speech is projected into the noise eigenspace, the noise energy is packed into a few dimensions with large eigenvalues, and those dimensions hopefully possess relatively less speech, because the speech energy distribution is usually different from noise energy distribution. The noise can be reduced by discarding those dimensions with large noise energy, while no significant loss occurs in speech. To track noise variation, the noise eigenspace is periodically updated, where the computation cost for eigenspace construction can be kept at an acceptable level. The proposed VAD was evaluated using the TIMIT database mixed with several noises. The experiment showed that the proposed VAD is more accurate than previous VADs in noisy environments.
収録刊行物
-
- Acoustical Science and Technology
-
Acoustical Science and Technology 28 (6), 413-423, 2007
一般社団法人 日本音響学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390001205089136384
-
- NII論文ID
- 110006437026
-
- NII書誌ID
- AA11501808
-
- ISSN
- 13475177
- 03694232
- 13463969
-
- NDL書誌ID
- 8973570
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- NDL-Digital
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可