Dual-path Transformer Network: Direct Context-aware Modeling For End-to-end Monaural Speech Separation
2020 · Jingjing Chen, Qirong Mao, Dong Liu
Abstract
The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent neural network, leading to suboptimal separation performance. In this paper, we propose a dual-path transformer network (DPTNet) for end-to-end speech separation, which introduces direct context-awareness in the modeling for speech sequences. By introduces a improved transformer, elements in speech sequences can interact directly, which enables DPTNet can model for the speech sequences with direct context-awareness. The improved transformer in our approach learns the order information of the speech sequences without positional encodings by incorporating a recurrent neural network into the original transformer. In addition, the structure of dual paths makes our model efficient for extremely long speech sequence modeling. Extensive experiments on benchmar
Authors
(none)
Tags
Stats
Related papers
- Lafurca: Iterative Refined Speech Separation Based On Context-aware Dual-path Parallel Bi-lstm (2020)0.00
- Dual-path Filter Network: Speaker-aware Modeling For Speech Separation (2021)3.58
- Multi-scale Feature Fusion Transformer Network For End-to-end Single Channel Speech Separation (2022)0.00
- Dual-path Mamba: Short And Long-term Bidirectional Selective Structured State Space Models For Speech Separation (2024)4.12
- Dpt-fsnet: Dual-path Transformer Based Full-band And Sub-band Fusion Network For Speech Enhancement (2021)0.00
- Tf-locoformer: Transformer With Local Modeling By Convolution For Speech Separation And Enhancement (2024)10.35
- Dual-path RNN: Efficient Long Sequence Modeling For Time-domain Single-channel Speech Separation (2019)21.06
- Attention Is All You Need In Speech Separation (2020)20.59