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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU144910" target="_blank" >RIV/00216305:26230/22:PU144910 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9747340" target="_blank" >https://ieeexplore.ieee.org/document/9747340</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP43922.2022.9747340" target="_blank" >10.1109/ICASSP43922.2022.9747340</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

In recent years, a number of time-domain speech separation methods have been proposed. However, most of them are very sensitive to the environments and wide domain coverage tasks. In this paper, from the time-frequency domain perspective, we propose a densely-connected pyramid complex convolutional network, termed DPCCN, to improve the robustness of speech separation under complicated conditions. Furthermore, we generalize the DPCCN to target speech extraction (TSE) by integrating a new specially designed speaker encoder. Moreover, we also investigate the robustness of DPCCN to unsupervised cross-domain TSE tasks. A Mixture-Remix approach is proposed to adapt the target domain acoustic characteristics for fine-tuning the source model. We evaluate the proposed methods not only under noisy and reverberant in-domain condition, but also in clean but cross-domain conditions. Results show that for both speech separation and extraction, the DPCCN-based systems achieve significantly better performance and robustness than the currently dominating time-domain methods, especially for the crossdomain tasks. Particularly, we find that the Mixture-Remix finetuning with DPCCN significantly outperforms the TD-SpeakerBeam for unsupervised cross-domain TSE, with around 3.5 dB SISNR improvement on target domain test set, without any source domain performance degradation.

Název v anglickém jazyce

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

Popis výsledku anglicky

In recent years, a number of time-domain speech separation methods have been proposed. However, most of them are very sensitive to the environments and wide domain coverage tasks. In this paper, from the time-frequency domain perspective, we propose a densely-connected pyramid complex convolutional network, termed DPCCN, to improve the robustness of speech separation under complicated conditions. Furthermore, we generalize the DPCCN to target speech extraction (TSE) by integrating a new specially designed speaker encoder. Moreover, we also investigate the robustness of DPCCN to unsupervised cross-domain TSE tasks. A Mixture-Remix approach is proposed to adapt the target domain acoustic characteristics for fine-tuning the source model. We evaluate the proposed methods not only under noisy and reverberant in-domain condition, but also in clean but cross-domain conditions. Results show that for both speech separation and extraction, the DPCCN-based systems achieve significantly better performance and robustness than the currently dominating time-domain methods, especially for the crossdomain tasks. Particularly, we find that the Mixture-Remix finetuning with DPCCN significantly outperforms the TD-SpeakerBeam for unsupervised cross-domain TSE, with around 3.5 dB SISNR improvement on target domain test set, without any source domain performance degradation.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

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

ISBN

978-1-6654-0540-9

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

7292-7296

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Singapore

Místo konání akce

Singapore

Datum konání akce

22. 5. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000864187907119