arXiv https://arxiv.org/abs/2408.13920v1
Browse files
README.md
CHANGED
|
@@ -20,11 +20,18 @@ tags:
|
|
| 20 |
# Arousal - Dominance - Valence
|
| 21 |
|
| 22 |
Speech Emotion Recognition model from combined use of [Wavlm](https://huggingface.co/3loi/SER-Odyssey-Baseline-WavLM-Multi-Attributes) / [wav2vec2](https://hf.rst.im/audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim).
|
| 23 |
-
Achieves `0.6760566` valence CCC on [MSP-Podcast](https://ecs.utdallas.edu/research/researchlabs/msp-lab/MSP-Podcast.html) Test 1. Used as teacher for [wav2small]().
|
| 24 |
|
| 25 |
|
| 26 |
|
| 27 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
<table style="width:500px">
|
| 29 |
<tr><th colspan=6 align="center" >CCC MSP Podcast v1.7</th></tr>
|
| 30 |
<tr><th colspan=3 align="center">Test 1</th><th colspan=3 align="center">Test 2</th></tr>
|
|
|
|
| 20 |
# Arousal - Dominance - Valence
|
| 21 |
|
| 22 |
Speech Emotion Recognition model from combined use of [Wavlm](https://huggingface.co/3loi/SER-Odyssey-Baseline-WavLM-Multi-Attributes) / [wav2vec2](https://hf.rst.im/audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim).
|
| 23 |
+
Achieves `0.6760566` valence CCC on [MSP-Podcast](https://ecs.utdallas.edu/research/researchlabs/msp-lab/MSP-Podcast.html) Test 1. Used as teacher for [wav2small](https://arxiv.org/abs/2408.13920v1).
|
| 24 |
|
| 25 |
|
| 26 |
|
| 27 |
+
# [arXiv](https://arxiv.org/abs/2408.13920v1)
|
| 28 |
+
|
| 29 |
+
```
|
| 30 |
+
Wav2Small: Distilling Wav2Vec2 to 72K parameters for Low-Resource Speech emotion recognition.
|
| 31 |
+
Dionyssos Kounadis-Bastian, Oliver Schrüfer, Anna Derington, Hagen Wierstorf, Florian Eyben, Felix Burkhardt, Björn Schuller.
|
| 32 |
+
2024, arXiV Preprint
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
<table style="width:500px">
|
| 36 |
<tr><th colspan=6 align="center" >CCC MSP Podcast v1.7</th></tr>
|
| 37 |
<tr><th colspan=3 align="center">Test 1</th><th colspan=3 align="center">Test 2</th></tr>
|