Detail publikace

DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation and Extraction

HAN, J. LONG, Y. BURGET, L. ČERNOCKÝ, J.

Originální název

DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation and Extraction

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In recent years, a number of time-domain speech separation methodshave been proposed. However, most of them are very sensitiveto the environments and wide domain coverage tasks. In thispaper, from the time-frequency domain perspective, we propose adensely-connected pyramid complex convolutional network, termedDPCCN, to improve the robustness of speech separation under complicatedconditions. Furthermore, we generalize the DPCCN to targetspeech extraction (TSE) by integrating a new specially designedspeaker encoder. Moreover, we also investigate the robustness ofDPCCN to unsupervised cross-domain TSE tasks. A Mixture-Remixapproach is proposed to adapt the target domain acoustic characteristicsfor fine-tuning the source model. We evaluate the proposedmethods not only under noisy and reverberant in-domain condition,but also in clean but cross-domain conditions. Results show that forboth speech separation and extraction, the DPCCN-based systemsachieve significantly better performance and robustness than the currentlydominating time-domain methods, especially for the crossdomaintasks. Particularly, we find that the Mixture-Remix finetuningwith DPCCN significantly outperforms the TD-SpeakerBeamfor unsupervised cross-domain TSE, with around 3.5 dB SISNR improvementon target domain test set, without any source domain performancedegradation.

Klíčová slova

DPCCN, Mixture-Remix, cross-domain, speech separation, unsupervised target speech extraction

Autoři

HAN, J.; LONG, Y.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

27. 5. 2022

Nakladatel

IEEE Signal Processing Society

Místo

Singapore

ISBN

978-1-6654-0540-9

Kniha

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Strany od

7292

Strany do

7296

Strany počet

5

URL

https://ieeexplore.ieee.org/document/9747340

BibTex

@inproceedings{BUT178382,
  author="Jiangyu {Han} and Yanhua {Long} and Lukáš {Burget} and Jan {Černocký}",
  title="DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation and Extraction",
  booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
  year="2022",
  pages="7292--7296",
  publisher="IEEE Signal Processing Society",
  address="Singapore",
  doi="10.1109/ICASSP43922.2022.9747340",
  isbn="978-1-6654-0540-9",
  url="https://ieeexplore.ieee.org/document/9747340"
}

Dokumenty

han_icassp2022_DPCCN_Densely-Connected_Pyramid_Complex_Convolutional_Network_for_Robust_Speech_Separation_and_Extraction.pdf