Papers › CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimization

CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimization

19 Dec 2019arXiv:1912.09254archive 2025-07-28

Jeroen Zegers, Hugo Van hamme

In recent years there have been many deep learning approaches towards the multi-speaker source separation problem. Most use Long Short-Term Memory - Recurrent Neural Networks (LSTM-RNN) or Convolutional Neural Networks (CNN) to model the sequential behavior of speech. In this paper we propose a novel network for source separation using an encoder-decoder CNN and LSTM in parallel. Hyper parameters have to be chosen for both parts of the network and they are potentially mutually dependent. Since hyper parameter grid search has a high computational burden, random search is often preferred. However, when sampling a new point in the hyper parameter space, it can potentially be very close to a previously evaluated point and thus give little additional information. Furthermore, random sampling is as likely to sample in a promising area as in an hyper space area dominated with poor performing models. Therefore, we use a Bayesian hyper parameter optimization technique and find that the parallel CNN-LSTM outperforms the LSTM-only and CNN-only model.

PaperPDFCode

Code

JeroenZegers/Nabu-MSSS officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderMulti-Speaker Source Separation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LSTMRandom SearchSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections