Packet loss concealment method based on hidden Markov model and decision tree for AMR-WB codec

Packet loss concealment (PLC) techniques are utilized to improve the quality of Voice over IP (VoIP) communications by reconstructing missing speech packets. Hidden Markov Model (HMM)-based PLC methods have shown a significant improvement over traditional methods by tracking the statistical evolution of speech signals. However, these methods may result in perceptually disturbing artifacts that arise from the structure of the HMM model. In this study, we introduce HMM-based PLC methods and investigate the impact of Markovian assumptions on their performance, specifically pitch fluctuation and gain mismatching. We then propose a new PLC method implemented on the G.722.2 codec, which incorporates the HMM and Decision Tree (DT) architecture. Our proposed architecture avoids the HMM's emissions dependencies assumption by using a DT layer, resulting in more accurate speech packet regeneration and natural transitions between the synthesized and concealed speech signals. The proposed method uses HMM and DT to track the statistical evolution of speech signals and accurately predict/estimate lost speech packets by exploiting the surrounding received speech packets. The proposed method is evaluated using mathematical proofs, objective, and subjective metrics, with results showing a considerable enhancement in speech quality compared to conventional PLC methods, achieving a Perceptual Evaluation of Speech Quality (PESQ) score higher than 3 at a 20% packet loss ratio.