Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses

Abstract: 

Speech enhancement has greatly benefited from deep learning. Currently, the best performing deep architectures use long short-term memory (LSTM) recurrent neural networks (RNNs) to model short and long temporal dependencies. These approaches, however, underutilize or ignore spectral-level dependencies within the magnitude and phase responses, respectively. In this paper, we propose a deep learning architecture that leverages both temporal and spectral dependencies within the magnitude and phase responses. More specifically, we first train a LSTM network to predict both the spectral-magnitude response and group delay, where this model captures temporal correlations. We then introduce Markovian recurrent connections in the output layers to capture spectral dependencies within the magnitude and phase responses. We compare our approach with traditional enhancement approaches and approaches that consider spectral dependencies within a single time frame. The results show that considering the within-frame spectral dependencies leads to improvements.

up
0 users have voted:

Paper Details

Authors:
Khandokar Md. Nayem, Donald S. Williamson
Submitted On:
15 May 2020 - 2:02am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Khandokar Md. Nayem
Paper Code:
SPE-L6.4
Document Year:
2020
Cite

Document Files

ICASSP 2020 presentation slides on Intra-spectral speech enhancement

(32)

Subscribe

[1] Khandokar Md. Nayem, Donald S. Williamson, "Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5337. Accessed: Sep. 22, 2020.
@article{5337-20,
url = {http://sigport.org/5337},
author = {Khandokar Md. Nayem; Donald S. Williamson },
publisher = {IEEE SigPort},
title = {Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses},
year = {2020} }
TY - EJOUR
T1 - Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses
AU - Khandokar Md. Nayem; Donald S. Williamson
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5337
ER -
Khandokar Md. Nayem, Donald S. Williamson. (2020). Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses. IEEE SigPort. http://sigport.org/5337
Khandokar Md. Nayem, Donald S. Williamson, 2020. Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses. Available at: http://sigport.org/5337.
Khandokar Md. Nayem, Donald S. Williamson. (2020). "Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses." Web.
1. Khandokar Md. Nayem, Donald S. Williamson. Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5337