Toggle Main Menu Toggle Search

Open Access padlockePrints

Monaural source separation based on adaptive discriminative criterion in neural networks

Lookup NU author(s): Dr Yang Sun, Lei Zhu, Professor Jonathon Chambers, Dr Mohsen Naqvi



© 2017 IEEE. Monaural source separation is an important research area which can help to improve the performance of several real-world applications, such as speech recognition and assisted living systems. Huang et al. proposed deep recurrent neural networks (DRNNs) with discriminative criterion objective function to improve the performance of source separation. However, the penalty factor in the objective function is selected randomly and empirically. Therefore, we introduce an approach to calculate the parameter in the discriminative term adaptively via the discrepancy between target features. The penalty factor can be changed with inputs to improve the separation performance. The proposed method is evaluated with different settings and architectures of neural networks. In these experiments, the TIMIT corpus is explored as the database and the signal to distortion ratio (SDR) as the measurement. Comparing with the previous approach, our method has improved robustness and a better separation performance.

Publication metadata

Author(s): Sun Y, Zhu L, Chambers JA, Naqvi SM

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: 22nd International Conference on Digital Signal Processing, DSP

Year of Conference: 2017

Online publication date: 07/11/2017

Acceptance date: 02/04/2016

Date deposited: 29/01/2018

ISSN: 2165-3577

Publisher: Institute of Electrical and Electronics Engineers Inc.


DOI: 10.1109/ICDSP.2017.8096100

Library holdings: Search Newcastle University Library for this item

ISBN: 9781538618950