.png){kind=icon}
.png){kind=icon}
Return
A speech prediction model based on codec modeling and transformer decoding
.png){kind=icon}
OA
AI
DOI：10.1016/j.csl.2025.101892.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a codec-based speech prediction approach that effectively leverages acoustic tokens and embeddings extracted from speech codecs. • We systematically evaluate the speech prediction performance of the proposed approach, and demonstrate that it outperforms recent baselines. • We investigate the factors that impact speech prediction performance and examine different training and inference strategies.
Keywords:
Speech prediction
Packet loss concealment
Speech codec
Speech inpainting
Transformer decoder
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
C
IF:
0
Papers:
43
Citations:
0