Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,9 @@ pipeline_tag: audio-to-audio
|
|
| 5 |
|
| 6 |
LLaSE: Maximizing Acoustic Preservation for LLaMA based Speech Enhancement
|
| 7 |
|
|
|
|
|
|
|
|
|
|
| 8 |
Abstract
|
| 9 |
Language Models (LMs) have shown strong capabilities in semantic understanding and contextual modeling, making them promising for speech enhancement.
|
| 10 |
Building on SELM, our previous work that first introduced LMs to speech enhancement, we note that SELM and other existing generative
|
|
|
|
| 5 |
|
| 6 |
LLaSE: Maximizing Acoustic Preservation for LLaMA based Speech Enhancement
|
| 7 |
|
| 8 |
+
Demo Page: https://kevin-naticl.github.io/LLaSE-Demopage/
|
| 9 |
+
Github: https://github.com/Kevin-naticl/LLaSE
|
| 10 |
+
|
| 11 |
Abstract
|
| 12 |
Language Models (LMs) have shown strong capabilities in semantic understanding and contextual modeling, making them promising for speech enhancement.
|
| 13 |
Building on SELM, our previous work that first introduced LMs to speech enhancement, we note that SELM and other existing generative
|