Single Channel Speech Separation using Enhanced Learning on Embedding Features

Ha Minh Tan, Jia Ching Wang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

1 引文 斯高帕斯(Scopus)

摘要

Speech separation has been utilized in many important applications such as automatic speech, mobile phones, hearing aids, and human-machine interactions. In particular, deep neural networks have been considered as a great potential for speech and music separation in recent years. In this paper, we propose a discriminative learning model to solve the single-channel speech separation. Firstly, deep clustering (DC) trains the embedding features. And then these features are utilized as the input for the deep neural network to directly isolate the component sources. The separation performances of the proposed model obtain 10.06 dB SDR, 16.50 dB SIR, 11.48 dB SAR, 9.06 dB SI-SNRi, 88% STOI, and 2.03 PESQ on the TSP dataset.

原文???core.languages.en_GB???
主出版物標題2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021
發行者Institute of Electrical and Electronics Engineers Inc.
頁面430-431
頁數2
ISBN(電子)9781665436762
DOIs
出版狀態已出版 - 2021
事件10th IEEE Global Conference on Consumer Electronics, GCCE 2021 - Kyoto, Japan
持續時間: 12 10月 202115 10月 2021

出版系列

名字2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???10th IEEE Global Conference on Consumer Electronics, GCCE 2021
國家/地區Japan
城市Kyoto
期間12/10/2115/10/21

指紋

深入研究「Single Channel Speech Separation using Enhanced Learning on Embedding Features」主題。共同形成了獨特的指紋。

引用此