AMRConvNet: AMR-Coded Speech Enhancement Using Convolutional Neural Networks
This addresses speech quality issues in 2G cellular phone calls, but it is incremental as it applies existing CNN methods to a specific coding scheme.
The paper tackled speech quality degradation in AMR-coded speech by proposing AMRConvNet, a convolutional neural network for artificial bandwidth expansion and enhancement, resulting in average MOS-LQO improvements of 0.425 points at 4.75k bitrate and 0.073 points at 12.2k bitrate.
Speech is converted to digital signals using speech coding for efficient transmission. However, this often lowers the quality and bandwidth of speech. This paper explores the application of convolutional neural networks for Artificial Bandwidth Expansion (ABE) and speech enhancement on coded speech, particularly Adaptive Multi-Rate (AMR) used in 2G cellular phone calls. In this paper, we introduce AMRConvNet: a convolutional neural network that performs ABE and speech enhancement on speech encoded with AMR. The model operates directly on the time-domain for both input and output speech but optimizes using combined time-domain reconstruction loss and frequency-domain perceptual loss. AMRConvNet resulted in an average improvement of 0.425 Mean Opinion Score - Listening Quality Objective (MOS-LQO) points for AMR bitrate of 4.75k, and 0.073 MOS-LQO points for AMR bitrate of 12.2k. AMRConvNet also showed robustness in AMR bitrate inputs. Finally, an ablation test showed that our combined time-domain and frequency-domain loss leads to slightly higher MOS-LQO and faster training convergence than using either loss alone.