Interleaved Multitask Learning For Audio Source Separation With Independent Databases

Abstract

Deep Neural Network-based source separation methods usually train independent models to optimize for the separation of individual sources. Although this can lead to good performance for well-defined targets, it can also be computationally expensive. The multitask alternative of a single network jointly optimizing for all targets simultaneously usually requires the availability of all target sources for each input. This requirement hampers the ability to create large training databases. In this paper, we present a model that decomposes the learnable parameters into a shared parametric model (encoder) and independent components (decoders) specific to each source. We propose an interleaved training procedure that optimizes the sub-task decoders independently and thus does not require each sample to possess a ground truth for all of its composing sources. Experimental results on MUSDB18 with the proposed method show comparable performance to independently trained models, with less trainabl

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydoire2019interleaved

Related papers

• Mmdenselstm: An Efficient Combination Of Convolutional And Recurrent Neural Networks For Audio Source Separation (2018)15.28
• Independence-based Joint Dereverberation And Separation With Neural Source Model (2021)4.52
• Unsupervised Music Source Separation Using Differentiable Parametric Source Models (2022)10.97
• Multichannel Audio Source Separation With Independent Deeply Learned Matrix Analysis Using Product Of Source Models (2021)0.00
• SADDEL: Joint Speech Separation And Denoising Model Based On Multitask Learning (2020)0.00
• Generalized Multichannel Variational Autoencoder For Underdetermined Source Separation (2018)7.81
• Audio Source Separation Via Multi-scale Learning With Dilated Dense U-nets (2019)0.00
• End-to-end Networks For Supervised Single-channel Speech Separation (2018)0.00