Dual-Signal Transformation LSTM Network for Real-Time Noise Suppression

This paper introduces a dual-signal transformation LSTM network (DTLN) for real-time speech enhancement as part of the Deep Noise Suppression Challenge (DNS-Challenge). This approach combines a short-time Fourier transform (STFT) and a learned analysis and synthesis basis in a stacked-network approach with less than one million parameters... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Speech Enhancement Deep Noise Suppression (DNS) Challenge DTLN SI-SDR 16.34 # 1
PESQ 3.04 # 3
ΔPESQ 0.61 # 3
Speech Enhancement WHAMR! DTLN SI-SDR 2.12 # 2
PESQ 2.23 # 1
ΔPESQ 0.4 # 1

Methods used in the Paper