Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement
Preprint
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 module, aiming to capture long-term temporal-frequency dependencies and further aggregate global hierarchical contextual information. Experimental results on Voice Bank + DEMAND demonstrate that DB-AIAT yields state-of-the-art performance (e.g., 3.31 PESQ, 95.6% STOI and 10.79dB SSNR) over previous advanced systems with a relatively small model size (2.81M).Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Glance and gaze: A collaborative learning framework for single-channel speech enhancementApplied Acoustics, 2022
- On the Compensation Between Magnitude and Phase in Speech SeparationIEEE Signal Processing Letters, 2021
- Learning Complex Spectral Mapping With Gated Convolutional Recurrent Networks for Monaural Speech EnhancementIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain2019
- Supervised Speech Separation Based on Deep Learning: An OverviewIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- A Regression Approach to Speech Enhancement Based on Deep Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- On Training Targets for Supervised Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- The importance of phase in speech enhancementSpeech Communication, 2011
- Evaluation of Objective Quality Measures for Speech EnhancementIEEE Transactions on Audio, Speech, and Language Processing, 2007