Blind and Neural Network-Guided Convolutional Beamformer for Joint Denoising, Dereverberation, and Source Separation

DOI DOI PDF 被引用文献2件 オープンアクセス

書誌事項

公開日
2021-06-06
権利情報
  • https://doi.org/10.15223/policy-029
  • https://doi.org/10.15223/policy-037
DOI
  • 10.1109/icassp39728.2021.9414264
  • 10.48550/arxiv.2108.01836
公開者
IEEE

説明

This paper proposes an approach for optimizing a Convolutional BeamFormer (CBF) that can jointly perform denoising (DN), dereverberation (DR), and source separation (SS). First, we develop a blind CBF optimization algorithm that requires no prior information on the sources or the room acoustics, by extending a conventional joint DR and SS method. For making the optimization computationally tractable, we incorporate two techniques into the approach: the Source-Wise Factorization (SW-Fact) of a CBF and the Independent Vector Extraction (IVE). To further improve the performance, we develop a method that integrates a neural network(NN) based source power spectra estimation with CBF optimization by an inverse-Gamma prior. Experiments using noisy reverberant mixtures reveal that our proposed method with both blind and NN-guided scenarios greatly outperforms the conventional state-of-the-art NN-supported mask-based CBF in terms of the improvement in automatic speech recognition and signal distortion reduction performance.

Accepted by IEEE ICASSP 2021

収録刊行物

被引用文献 (2)*注記

もっと見る

キーワード

問題の指摘

ページトップへ