RECALL NEURAL NETWORK FOR SOURCE SEPARATION

檔案

本條目沒有附加檔案。

日期

2018-01-01

期刊名稱

2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)

卷期與頁次

頁 2956–2960

語言

英文

摘要

This paper presents a novel memory-augmented neural network for single-channel source separation. We propose a recall neural network (RCNN) where a couple of external memories are realized for sequence-to-sequence learning based on an encoder and a decoder. These memories are learned in a two-pass sensing procedure where the mixed signal is encoded and then decoded (or recalled) as context vectors by using a bidirectional long short-term memory (LSTM) and a LSTM, respectively. These context vectors are integrated in a gating layer. A set of attention weights are calculated to attend the hidden state of decoder to implement a recurrent neural network for source separation. A gated attention mechanism is carried out to fulfill a specialized memory network. The regression errors due to two passes of sensing procedure and one pass of gated attention are jointly minimized to estimate the weight parameters of different components in different layers. The experiments on multi-speaker speech enhancement show that the proposed RCNN consistently outperforms LSTM and neural Turing machine in different settings.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Chien, J.-T., & Tsou, K.-W. (2018). RECALL NEURAL NETWORK FOR SOURCE SEPARATION. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2956–2960. https://ir.lib.nycu.edu.tw/handle/11536/150763

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/150763