CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimization
This work addresses the problem of separating overlapping speech signals for audio processing applications, but it is incremental as it combines existing CNN and LSTM methods with optimization techniques.
The paper tackles multi-speaker source separation by proposing a parallel CNN-LSTM network and uses Bayesian hyperparameter optimization to improve performance, achieving better results than LSTM-only or CNN-only models.
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.