PostGAN: A GAN-Based Post-Processor to Enhance the Quality of Coded Speech
This work addresses speech quality enhancement for low-bitrate Bluetooth codecs, representing an incremental improvement over existing data-driven post-processors.
The paper tackled the problem of speech quality degradation in low-bitrate transform coding by proposing PostGAN, a GAN-based neural post-processor that improved coded speech quality by around 20 MUSHRA points on the LC3 codec at 16 kbit/s.
The quality of speech coded by transform coding is affected by various artefacts especially when bitrates to quantize the frequency components become too low. In order to mitigate these coding artefacts and enhance the quality of coded speech, a post-processor that relies on a-priori information transmitted from the encoder is traditionally employed at the decoder side. In recent years, several data-driven post-postprocessors have been proposed which were shown to outperform traditional approaches. In this paper, we propose PostGAN, a GAN-based neural post-processor that operates in the sub-band domain and relies on the U-Net architecture and a learned affine transform. It has been tested on the recently standardized low-complexity, low-delay bluetooth codec (LC3) for wideband speech at the lowest bitrate (16 kbit/s). Subjective evaluations and objective scores show that the newly introduced post-processor surpasses previously published methods and can improve the quality of coded speech by around 20 MUSHRA points.