Please use this identifier to cite or link to this item:
Title: Single channel speech separation with constrained utterance level permutation invariant training using grid LSTM
Authors: Xu, Chenglin
Rao, Wei
Xiao, Xiong
Chng, Eng Siong
Li, Haizhou
Keywords: Engineering::Computer science and engineering
Issue Date: 2018
Source: Xu, C., Rao, W., Xiao, X., Chng, E. S., & Li, H. (2018). Single channel speech separation with constrained utterance level permutation invariant training using grid LSTM. Proceedings of 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6-10. doi:10.1109/icassp.2018.8462471
Abstract: Utterance level permutation invariant training (uPIT) technique is a state-of-the-art deep learning architecture for speaker independent multi-talker separation. uPIT solves the label ambiguity problem by minimizing the mean square error (MSE) over all permutations between outputs and targets. However, uPIT may be sub-optimal at segmental level because the optimization is not calculated over the individual frames. In this paper, we propose a constrained uPIT (cuPIT) to solve this problem by computing a weighted MSE loss using dynamic information (i.e., delta and acceleration). The weighted loss ensures the temporal continuity of output frames with the same speaker. Inspired by the heuristics (i.e., vocal tract continuity) in computational auditory scene analysis, we then extend the model by adding a Grid LSTM layer, that we name it as cuPIT-Grid LSTM, to automatically learn both temporal and spectral patterns over the input magnitude spectrum simultaneously. The experimental results show 9.6% and 8.5% relative improvements on WSJ0-2mix dataset under both closed and open conditions comparing with the uPIT baseline.
ISBN: 9781538646588
DOI: 10.1109/ICASSP.2018.8462471
Rights: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Citations 5

Updated on Feb 4, 2023

Page view(s)

Updated on Feb 4, 2023

Download(s) 20

Updated on Feb 4, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.