Contents

Convolutional Recurrent Network

Towards efficient models for real-time deep noise suppression

Notes > ABSTRACT

Reasonably small recurrent and Convolutional Recurrent Network

Notes > ABSTRACT

Evaluated Convolutional Recurrent Network architectures

Notes > INTRODUCTION > Models

Convolutional Recurrent Network and Convolutional Neural Networks raised performance but enormously large architectures NOTE: (with ref: (Luo and Mesgarani 2019 ) ) time domain networks can in THEORY produce better results than frequency domain networks but not yet realized.

Bibliography

Luo, Yi, and Nima Mesgarani. 2019. “Conv-Tasnet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation.” IEEE/ACM Transactions on Audio, Speech, and Language Processing 27 (8):1256–66. https://doi.org/10.1109/taslp.2019.2915167.