Dual-branch Attention-in-attention Transformer For Single-channel Speech Enhancement
2021 · Guochen Yu, Andong Li, Chengshi Zheng, et al.
Abstract
Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance. Motivated by that, we propose a dual-branch attention-in-attention transformer dubbed DB-AIAT to handle both coarse- and fine-grained regions of the spectrum in parallel. From a complementary perspective, a magnitude masking branch is proposed to coarsely estimate the overall magnitude spectrum, and simultaneously a complex refining branch is elaborately designed to compensate for the missing spectral details and implicitly derive phase information. Within each branch, we propose a novel attention-in-attention transformer-based module to replace the conventional RNNs and temporal convolutional networks for temporal sequence modeling. Specifically, the proposed attention-in-attention transformer consists of adaptive temporal-frequency attention transformer blocks and an adaptive hierarchical attention mod
Authors
(none)
Tags
Stats
Related papers
- Dbt-net: Dual-branch Federative Magnitude And Phase Estimation With Attention-in-attention Transformer For Monaural Speech Enhancement (2022)12.47
- Monaural Speech Enhancement Using A Multi-branch Temporal Convolutional Network (2019)3.58
- Full Attention Bidirectional Deep Learning Structure For Single Channel Speech Enhancement (2021)0.00
- Improving Transformer-based Conversational ASR By Inter-sentential Attention Mechanism (2022)7.50
- Efficient Encoder-decoder And Dual-path Conformer For Comprehensive Feature Learning In Speech Enhancement (2023)7.16
- Attention-based ASR With Lightweight And Dynamic Convolutions (2019)9.03
- PCNN: A Lightweight Parallel Conformer Neural Network For Efficient Monaural Speech Enhancement (2023)6.77
- Multi-frequency Information Enhanced Channel Attention Module For Speaker Representation Learning (2022)0.00