Plugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired By Dynamic Neural Network
2024 · Yanan Chen, Zihao Cui, Yingying Gao, et al.
Abstract
The expectation to deploy a universal neural network for speech enhancement, with the aim of improving noise robustness across diverse speech processing tasks, faces challenges due to the existing lack of awareness within static speech enhancement frameworks regarding the expected speech in downstream modules. These limitations impede the effectiveness of static speech enhancement approaches in achieving optimal performance for a range of speech processing tasks, thereby challenging the notion of universal applicability. The fundamental issue in achieving universal speech enhancement lies in effectively informing the speech enhancement module about the features of downstream modules. In this study, we present a novel weighting prediction approach, which explicitly learns the task relationships from downstream training information to address the core challenge of universal speech enhancement. We found the role of deciding whether to employ data augmentation techniques as crucial downstr
Authors
(none)
Tags
Stats
Related papers
- The Potential Of Neural Speech Synthesis-based Data Augmentation For Personalized Speech Enhancement (2022)6.77
- Multi-cmgan+/+: Leveraging Multi-objective Speech Quality Metric Prediction For Speech Enhancement (2023)0.00
- A Network Of Deep Neural Networks For Distant Speech Recognition (2017)10.35
- Toward Universal Speech Enhancement For Diverse Input Conditions (2023)0.00
- Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement (2022)0.00
- Weighted Speech Distortion Losses For Neural-network-based Real-time Speech Enhancement (2020)14.51
- Dense-tsnet: Dense Connected Two-stage Structure For Ultra-lightweight Speech Enhancement (2024)0.00
- Dbnet: A Dual-branch Network Architecture Processing On Spectrum And Waveform For Single-channel Speech Enhancement (2021)8.09