Wavecrn: An Efficient Convolutional Recurrent Neural Network For End-to-end Speech Enhancement

Abstract

Due to the simple design pipeline, end-to-end (E2E) neural models for speech enhancement (SE) have attracted great interest. In order to improve the performance of the E2E model, the locality and temporal sequential properties of speech should be efficiently taken into account when modelling. However, in most current E2E models for SE, these properties are either not fully considered or are too complex to be realized. In this paper, we propose an efficient E2E SE model, termed WaveCRN. In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the temporal sequential property of the locality feature is modeled by stacked simple recurrent units (SRU). Unlike a conventional temporal sequential model that uses a long short-term memory (LSTM) network, which is difficult to parallelize, SRU can be efficiently parallelized in calculation with even fewer model parameters. In addition, in order to more effectively suppress the noise components in the inp

Stats

• citations73
• S2 citations—
• github stars0
• HF likes0
• heat score14.02
• arxiv keyhsieh2020wavecrn

Related papers

• Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks (2020)5.84
• Effcrn: An Efficient Convolutional Recurrent Network For High-performance Speech Enhancement (2023)5.84
• Inplace Gated Convolutional Recurrent Neural Network For Dual-channel Speech Enhancement (2021)0.00
• Multichannel Speech Enhancement By Raw Waveform-mapping Using Fully Convolutional Networks (2019)12.25
• Segmental Recurrent Neural Networks For End-to-end Speech Recognition (2016)0.00
• A Fully Recurrent Feature Extraction For Single Channel Speech Enhancement (2020)0.00
• Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network For Speech Enhancement (2021)0.00
• A Dual-staged Context Aggregation Method Towards Efficient End-to-end Speech Enhancement (2019)0.00