Unsupervised Adaptation of Neural Networks for Discriminative Sound Source Localization with Eliminative Constraint

Ryu Takeda, Yoshiki Kudo, Kazuki Takashima, Yoshifumi Kitamura, Kazunori Komatani

研究成果: Conference contribution

10 被引用数 (Scopus)

抄録

This paper describes an unsupervised adaptation method of deep neural networks (DNNs) regarding discriminative sound source localization (SSL). DNNs-based SSL and its unsupervised adaptation fail under different conditions from those during training. The estimations sometimes include incoherent unpredictable errors due to the NN's non-linearity. We propose an eliminative posterior probability constraint using a model-based SSL for unsupervised DNNs adaptation. This constraint forces the probability of 'less possible candidates' to become zero to eliminate incoherent errors. The candidates are indicated by a model-based SSL method because it can estimate the azimuth of the sound source with moderate accuracy and explicit reasoning. As a result, the localization performance of adapted DNNs improved more than that of model-based SSL. Experimental results showed that our method improved localization correctness of 1D azimuth and 3D regions by a maximum of 13.3 and 5.9 points compared with the model-based SSL.

本文言語English
ホスト出版物のタイトル2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3514-3518
ページ数5
ISBN(印刷版)9781538646588
DOI
出版ステータスPublished - 2018 9月 10
イベント2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Calgary, Canada
継続期間: 2018 4月 152018 4月 20

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2018-April
ISSN(印刷版)1520-6149

Other

Other2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
国/地域Canada
CityCalgary
Period18/4/1518/4/20

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Unsupervised Adaptation of Neural Networks for Discriminative Sound Source Localization with Eliminative Constraint」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル