แนวคิดหลัก
SSL representations have limited value in improving on-device speech enhancement systems under low-SNR conditions.
สถิติ
"Our constraints are designed around on-device real-time speech enhancement – model is causal, the compute footprint is small."
"In particular, we study the popular wav2vec2.0 SSL model and attempt to utilize it to improve a GCRN based on-device SE model."
"The GCRN neural architecture can be used to design and develop an SE models satisfying these characteristics."
คำพูด
"Our goal in this paper is to systematically investigate different ways of using SSL embeddings to improve an SE system."
"SSL models are usually very large, non-causal and hence fine-tuning them is not a possible path for using them in our case."