Learning Complex Spectral Mapping with Gated Convolutional Recurrent Networks for Monaural Speech Enhancement

By Ke Tan, Deliang Wang. IEEE/ACM Transactions on Audio Speech and Language Processing, 2019

363 citations recorded by the source corpus.

Phase is important for perceptual quality of speech. However, it seems intractable to directly estimate phase spectra through supervised learning due to their lack of spectrotemporal structure in it. Complex spectral mapping aims to estimate the real and imaginary spectrograms of clean speech from those of noisy speech, which simultaneously enhances magnitude and phase responses of speech. Inspired by multi-task learning, we propose a gated convolutional recurrent network (GCRN) for complex spectral mapping, which amounts to a causal system for monaural speech enhancement. Our experimental results suggest that the proposed GCRN substantially outperforms an existing convolutional neural network (CNN) for complex spectral mapping in terms of both objective speech intelligibility and quality. Moreover, the proposed approach yields significantly higher STOI and PESQ than magnitude spectral mapping and complex ratio masking. We also find that complex spectral mapping with the proposed GCRN provides an effective phase estimate.

Subfields: Cognitive Neuroscience, Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/fbe3a0f5ae9b4c3d464439bef5b13d13d4e1199a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. Ke Tan
2. Anurag Kumar

In Computational Mechanics

1. Ke Tan
2. Anurag Kumar

In Signal Processing

1. Ke Tan
2. Xuyi Zhuang
3. Zehua Zhang
4. Yukun Qian
5. Heng Li
6. Lu Zhang
7. Mingjiang Wang
8. Anurag Kumar

Citations in the corpus

• Torchaudio-Squim: Reference-Less Speech Quality and Intelligibility Measures in Torchaudio (2023, background): “These speech enhancement systems are based on the GCRN architecture [30], with varying degree of performances due to different configurations.”
• FB-MSTCN: A Full-Band Single-Channel Speech Enhancement Method Based on Multi-Scale Temporal Convolutional Network (2022, methodology): “For example, in wide-band real-time scenarios, most methods [4, 5, 6, 7] have the input frame size set to 20 ms or 32 ms, corresponding to 320 and 512 points of Fourier transform analysis, respectively.”