holylovenia commited on
Commit
e235189
1 Parent(s): 366dc06

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -0
README.md CHANGED
@@ -1,3 +1,43 @@
1
  ---
2
  license: cc-by-sa-4.0
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-sa-4.0
3
+ datasets:
4
+ - Ar4ikov/iemocap_audio_text_splitted
5
+ language:
6
+ - en
7
+ - zh
8
+ metrics:
9
+ - f1
10
+ library_name: transformers
11
+ pipeline_tag: audio-classification
12
+ tags:
13
+ - speech-emotion-recognition
14
  ---
15
+
16
+ # Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition
17
+
18
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on English and Chinese data from adult speakers.
19
+ The model is trained on the training sets of [CREMA-D](https://github.com/CheyneyComputerScience/CREMA-D), [ESD](https://github.com/HLTSingapore/Emotional-Speech-Data), [IEMOCAP](https://sail.usc.edu/iemocap/iemocap_release.htm), and [TESS](https://www.kaggle.com/datasets/ejlok1/toronto-emotional-speech-set-tess).
20
+ When using this model, make sure that your speech input is sampled at 16kHz.
21
+
22
+ The scripts used for training and evaluation can be found here:
23
+ [https://github.com/HLTCHKUST/elderly_ser/tree/main](https://github.com/HLTCHKUST/elderly_ser/tree/main)
24
+
25
+ ## Evaluation Results
26
+
27
+ For the details (e.g., the statistics of `train`, `valid`, and `test` data), please refer to our paper on [arXiv](https://arxiv.org/abs/2306.14517).
28
+ It also provides the model's speech emotion recognition performances on: English-All, Chinese-All, English-Elderly, Chinese-Elderly, English-Adults, Chinese-Adults.
29
+
30
+ ## Citation
31
+
32
+ Our paper will be published at INTERSPEECH 2023. In the meantime, you can find our paper on [arXiv](https://arxiv.org/abs/2306.14517).
33
+ If you find our work useful, please consider citing our paper as follows:
34
+ ```
35
+ @misc{cahyawijaya2023crosslingual,
36
+ title={Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition},
37
+ author={Samuel Cahyawijaya and Holy Lovenia and Willy Chung and Rita Frieske and Zihan Liu and Pascale Fung},
38
+ year={2023},
39
+ eprint={2306.14517},
40
+ archivePrefix={arXiv},
41
+ primaryClass={cs.CL}
42
+ }
43
+ ```