Full Attention Bidirectional Deep Learning Structure For Single Channel Speech Enhancement

Abstract

As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper, a new deep learning structure for speech enhancement is demonstrated. The model introduces a "full" attention mechanism to a bidirectional sequence-to-sequence method to make use of latent information after each focal frame. This is an extension of the previous attention-based RNN method. The proposed bidirectional attention-based architecture achieves better performance in terms of speech quality (PESQ), compared with OM-LSA, CNN-LSTM, T-GSA and the unidirectional attention-based LSTM baseline.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyan2021full

Related papers

• Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement (2022)0.00
• Multi-modal Hybrid Deep Neural Network For Speech Enhancement (2016)0.00
• Lmfca-net: A Lightweight Model For Multi-channel Speech Enhancement With Efficient Narrow-band And Cross-band Attention (2025)3.58
• Monaural Speech Enhancement Using A Multi-branch Temporal Convolutional Network (2019)3.58
• Efficient Encoder-decoder And Dual-path Conformer For Comprehensive Feature Learning In Speech Enhancement (2023)7.16
• Dual-branch Attention-in-attention Transformer For Single-channel Speech Enhancement (2021)14.83
• Encoder-decoder With Focus-mechanism For Sequence Labelling Based Spoken Language Understanding (2016)0.00
• FB-MSTCN: A Full-band Single-channel Speech Enhancement Method Based On Multi-scale Temporal Convolutional Network (2022)6.77