Lafurca: Iterative Refined Speech Separation Based On Context-aware Dual-path Parallel Bi-lstm

Abstract

Deep neural network with dual-path bi-directional long short-term memory (BiLSTM) block has been proved to be very effective in sequence modeling, especially in speech separation, e.g. DPRNN-TasNet \cite\{luo2019dual\}. In this paper, we propose several improvements of dual-path BiLSTM based network for end-to-end approach to monaural speech separation. Firstly a dual-path network with intra-parallel BiLSTM and inter-parallel BiLSTM components is introduced to reduce performance sub-variances among different branches. Secondly, we propose to use global context aware inter-intra cross-parallel BiLSTM to further perceive the global contextual information. Finally, a spiral multi-stage dual-path BiLSTM is proposed to iteratively refine the separation results of the previous stages. All these networks take the mixed utterance of two speakers and map it to two separate utterances, where each utterance contains only one speaker's voice. For the objective, we propose to train the network by d

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshi2020lafurca

Related papers

• Dual-path Transformer Network: Direct Context-aware Modeling For End-to-end Monaural Speech Separation (2020)18.24
• Speech Separation Based On Multi-stage Elaborated Dual-path Deep Bilstm With Auxiliary Identity Loss (2020)9.77
• Furcanext: End-to-end Monaural Speech Separation With Dynamic Gated Dilated Temporal Convolutional Networks (2019)12.40
• Dual-path Filter Network: Speaker-aware Modeling For Speech Separation (2021)3.58
• Embedding Recurrent Layers With Dual-path Strategy In A Variant Of Convolutional Network For Speaker-independent Speech Separation (2022)4.52
• Multi-scale Feature Fusion Transformer Network For End-to-end Single Channel Speech Separation (2022)0.00
• Dual-path RNN: Efficient Long Sequence Modeling For Time-domain Single-channel Speech Separation (2019)21.06
• Speech Separation Using An Asynchronous Fully Recurrent Convolutional Neural Network (2021)0.00