Parameter Enhancement for MELP Speech Codec in Noisy Communication Environment
This work addresses speech quality in noisy environments for communication systems, but it is incremental as it builds on existing MELP codec frameworks with a novel parameter enhancement approach.
The paper tackled the problem of noisy speech communication by proposing a deep learning-based method to directly enhance MELP codec parameters, achieving similar performance quality with much lower computational complexity than conventional time-frequency mask-based methods.
In this paper, we propose a deep learning (DL)-based parameter enhancement method for a mixed excitation linear prediction (MELP) speech codec in noisy communication environment. Unlike conventional speech enhancement modules that are designed to obtain clean speech signal by removing noise components before speech codec processing, the proposed method directly enhances codec parameters on either the encoder or decoder side. As the proposed method has been implemented by a small network without any additional processes required in conventional enhancement systems, e.g., time-frequency (T-F) analysis/synthesis modules, its computational complexity is very low. By enhancing the noise-corrupted codec parameters with the proposed DL framework, we achieved an enhancement system that is much simpler and faster than conventional T-F mask-based speech enhancement methods, while the quality of its performance remains similar.