Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio Signal ProcessingSpeech Enhancementspeech-recognitionSpeech RecognitionSpeech SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling
Standard Transformers use a single self-attention pathway to model both global dependencies and local patterns, creating tension between long-range structural reasoning and fine-grained local representation learning. We …
Representation LearningPerception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluating different SR algorithms are limited.…
Image Quality AssessmentImage Super-ResolutionBidirectional Cross-Attention Fusion of High-Resolution RGB and Low-Resolution Hyperspectral Inputs for Multimodal Semantic Segmentation
Multimodal semantic segmentation with heterogeneous sensors must reconcile complementary information across modalities that differ in spatial resolution and channel dimensionality. In particular, high-resolution RGB imag…
Semantic SegmentationPaperNet: Efficient Temporal Convolutions and Channel Residual Attention for EEG Epilepsy Detection
Electroencephalography (EEG) signals contain rich temporal-spectral structure but are difficult to model due to noise, subject variability, and multi-scale dynamics. Lightweight deep learning models have shown promise, y…
A Prospective Approach for Human-to-Human Interaction Recognition from Wi-Fi Channel Data using Attention Bidirectional Gated Recurrent Neural Network with GUI Application Implementation
Human Activity Recognition (HAR) research has gained significant momentum due to recent technological advancements, artificial intelligence algorithms, the need for smart cities, and socioeconomic transformation. However…
Activity RecognitionHuman Activity RecognitionHuman Interaction RecognitionTime Series Analysis