Update README.md
Browse files
README.md
CHANGED
|
@@ -70,10 +70,15 @@ The fine tuning data used to produce this model (VoxCeleb, VCTK) are mostly in e
|
|
| 70 |
|
| 71 |
# Publication
|
| 72 |
Details about the method used to build this model have been published at Interspeech 2024 in the paper entitled
|
| 73 |
-
[Disentangling prosody and timbre embeddings via voice conversion](https://www.isca-archive.org/interspeech_2024/gengembre24_interspeech.pdf).
|
| 74 |
|
| 75 |
Please consider citing this paper if you use this model in your own research work.
|
| 76 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
### Citation
|
| 78 |
Gengembre, N., Le Blouch, O., Gendrot, C. (2024) Disentangling prosody and timbre embeddings via voice conversion. Proc. Interspeech 2024, 2765-2769, doi: 10.21437/Interspeech.2024-207
|
| 79 |
|
|
|
|
| 70 |
|
| 71 |
# Publication
|
| 72 |
Details about the method used to build this model have been published at Interspeech 2024 in the paper entitled
|
| 73 |
+
[Disentangling prosody and timbre embeddings via voice conversion](https://www.isca-archive.org/interspeech_2024/gengembre24_interspeech.pdf).
|
| 74 |
|
| 75 |
Please consider citing this paper if you use this model in your own research work.
|
| 76 |
|
| 77 |
+
In this paper the model is denoted as W-PRO. The other two models used in this study can also be found on HuggingFace :
|
| 78 |
+
- [W-TBR](https://huggingface.co/Orange/Speaker-wavLM-tbr) for timber related embeddings
|
| 79 |
+
- [W-SPK](https://huggingface.co/Orange/Speaker-wavLM-id) for speaker embeddings (ASV)
|
| 80 |
+
|
| 81 |
+
|
| 82 |
### Citation
|
| 83 |
Gengembre, N., Le Blouch, O., Gendrot, C. (2024) Disentangling prosody and timbre embeddings via voice conversion. Proc. Interspeech 2024, 2765-2769, doi: 10.21437/Interspeech.2024-207
|
| 84 |
|