Constrained Convolutional-recurrent Networks To Improve Speech Quality With Low Impact On Recognition Accuracy

Abstract

For a speech-enhancement algorithm, it is highly desirable to simultaneously improve perceptual quality and recognition rate. Thanks to computational costs and model complexities, it is challenging to train a model that effectively optimizes both metrics at the same time. In this paper, we propose a method for speech enhancement that combines local and global contextual structures information through convolutional-recurrent neural networks that improves perceptual quality. At the same time, we introduce a new constraint on the objective function using a language model/decoder that limits the impact on recognition rate. Based on experiments conducted with real user data, we demonstrate that our new context-augmented machine-learning approach for speech enhancement improves PESQ and WER by an additional 24.5% and 51.3%, respectively, when compared to the best-performing methods in the literature.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyfakoor2018constrained

Related papers

• A Dual-staged Context Aggregation Method Towards Efficient End-to-end Speech Enhancement (2019)0.00
• Contextnet: Improving Convolutional Neural Networks For Automatic Speech Recognition With Global Context (2020)17.24
• Distortionless Multi-channel Target Speech Enhancement For Overlapped Speech Recognition (2020)0.00
• Speech Dereverberation With Context-aware Recurrent Neural Networks (2017)10.35
• Convolutional Recurrent Neural Network Based Progressive Learning For Monaural Speech Enhancement (2019)0.00
• A Fully Recurrent Feature Extraction For Single Channel Speech Enhancement (2020)0.00
• Effcrn: An Efficient Convolutional Recurrent Network For High-performance Speech Enhancement (2023)5.84
• Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network For Speech Enhancement (2021)0.00