Stochastic Markov Recurrent Neural Network for Source Separation

Jen-Tzung Chien, Che Yu Kuo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Monaural source separation based on recurrent neural network is learned to characterize the sequential patterns in source signals based on dynamic states which are propagated through time. The hidden states are assumed to be deterministic along a single path where a shared long short-term memory (LSTM) is used. Such assumptions may not faithfully reflect the randomness and the variety of temporal features in mixed signals. To strengthen the capability of LSTM in source separation, we propose a stochastic Markov LSTM where the regression from the mixed signal to its source signals is learned with a stochastic indicator of Markov state which selects the state-dependent LSTM for signal separation at each time. A set of LSTMs is discovered to capture the structural diversity of temporal signals or the stochastic trajectory of state transitions for sequential prediction. A new state machine is constructed to learn the complicated latent semantics in heterogeneous and structural mappings between mixed signals and source signals. The Gumbel-softmax sampling is implemented in the backpropagation algorithm with discrete Markov states. Experiments on speech enhancement illustrate the merit of the proposed stochastic Markov LSTM in terms of short-term objective intelligibility measure of the separated speech.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8072-8076
Number of pages5
ISBN (Electronic)9781479981311
DOIs
StatePublished - 1 May 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 12 May 201917 May 2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period12/05/1917/05/19

Keywords

  • Markov state
  • Source separation
  • deep sequential learning
  • latent variable model
  • stochastic transition

Fingerprint Dive into the research topics of 'Stochastic Markov Recurrent Neural Network for Source Separation'. Together they form a unique fingerprint.

  • Cite this

    Chien, J-T., & Kuo, C. Y. (2019). Stochastic Markov Recurrent Neural Network for Source Separation. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 8072-8076). [8683060] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8683060