News

• [Oct. 2024] 🔧 We update the usage in the FunASR interface with source selection. "ms" or "modelscope" for China mainland users; "hf" or "huggingface" for other overseas users. We recommend using FunASR interface for a smooth landing.
• [Jun. 2024] 🔧 We fix a bug in emotion2vec+. Please re-pull the latest code.
• [May. 2024] 🔥 Speech emotion recognition foundation model: emotion2vec+, with 9-class emotions has been released on Model Scope and Hugging Face. Check out a series of emotion2vec+ (seed, base, large) models for SER with high performance (We recommend this release instead of the Jan. 2024 release).
• [Jan. 2024] 9-class emotion recognition model with iterative fine-tuning from emotion2vec has been released in modelscope and FunASR.
• [Jan. 2024] emotion2vec has been integrated into modelscope and FunASR.
• [Dec. 2023] We release the paper, and create a WeChat group for emotion2vec.
• [Nov. 2023] We release code, checkpoints, and extracted features for emotion2vec.

Model Card

GitHub Repo: emotion2vec

Overview

• emotion2vec+: speech emotion recognition foundation model
  • Guides
  • Data Engineering
  • Performance
  • Inference with checkpoints
    • Install from FunASR
• emotion2vec: universal speech emotion representation model
  • Guides
  • Performance
    • Performance on IEMOCAP
    • Performance on other languages
    • Performance on other speech emotion tasks
  • Visualization
  • Extract features
    • Download extracted features
    • Extract features from your dataset
      • Install from the source code
      • Install from FunASR
  • Training your downstream model
  • Contributors
  • Citation

emotion2vec+: speech emotion recognition foundation model

Guides

emotion2vec+ is a series of foundational models for speech emotion recognition (SER). We aim to train a "whisper" in the field of speech emotion recognition, overcoming the effects of language and recording environments through data-driven methods to achieve universal, robust emotion recognition capabilities. The performance of emotion2vec+ significantly exceeds other highly downloaded open-source models on Hugging Face.

Data Engineering

We offer 3 versions of emotion2vec+, each derived from the data of its predecessor. If you need a model focusing on spech emotion representation, refer to emotion2vec: universal speech emotion representation model.

• emotion2vec+ seed: Fine-tuned with academic speech emotion data from EmoBox
• emotion2vec+ base: Fine-tuned with filtered large-scale pseudo-labeled data to obtain the base size model (~90M)
• emotion2vec+ large: Fine-tuned with filtered large-scale pseudo-labeled data to obtain the large size model (~300M)

The iteration process is illustrated below, culminating in the training of the emotion2vec+ large model with 40k out of 160k hours of speech emotion data. Details of data engineering will be announced later.

Performance

Performance on EmoBox for 4-class primary emotions (without fine-tuning). Details of model performance will be announced later.

Inference with checkpoints

Install from FunASR

1. install funasr

pip install -U funasr

2. run the code.

'''
Using the finetuned emotion recognization model

rec_result contains {'feats', 'labels', 'scores'}
	extract_embedding=False: 9-class emotions with scores
	extract_embedding=True: 9-class emotions with scores, along with features

9-class emotions: 
iic/emotion2vec_plus_seed, iic/emotion2vec_plus_base, iic/emotion2vec_plus_large (May. 2024 release)
iic/emotion2vec_base_finetuned (Jan. 2024 release)
    0: angry
    1: disgusted
    2: fearful
    3: happy
    4: neutral
    5: other
    6: sad
    7: surprised
    8: unknown
'''

from funasr import AutoModel

# model="iic/emotion2vec_base"
# model="iic/emotion2vec_base_finetuned"
# model="iic/emotion2vec_plus_seed"
# model="iic/emotion2vec_plus_base"
model_id = "iic/emotion2vec_plus_large"

model = AutoModel(
    model=model_id,
    hub="ms",  # "ms" or "modelscope" for China mainland users; "hf" or "huggingface" for other overseas users
)

wav_file = f"{model.model_path}/example/test.wav"
rec_result = model.generate(wav_file, output_dir="./outputs", granularity="utterance", extract_embedding=False)
print(rec_result)

The model will be downloaded automatically.

FunASR support file list input in wav.scp (kaldi style):

wav_name1 wav_path1.wav
wav_name2 wav_path2.wav
...

Refer to FunASR for more details.

emotion2vec: universal speech emotion representation model

Guides

emotion2vec is the first universal speech emotion representation model. Through self-supervised pre-training, emotion2vec has the ability to extract emotion representation across different tasks, languages, and scenarios.

Performance

Performance on IEMOCAP

emotion2vec achieves SOTA with only linear layers on the mainstream IEMOCAP dataset. Refer to the paper for more details.

Performance on other languages

emotion2vec achieves SOTA compared with SOTA SSL models on multiple languages (Mandarin, French, German, Italian, etc.). Refer to the paper for more details.

Performance on other speech emotion tasks

Refer to the paper for more details.

Visualization

UMAP visualizations of learned features on the IEMOCAP dataset. Red and Blue tones mean low and high arousal emotional classes, respectively. Refer to the paper for more details.

Extract features

Download extracted features

We provide the extracted features of popular emotion dataset IEMOCAP. The features are extracted from the last layer of emotion2vec. The features are stored in .npy format and the sample rate of the extracted features is 50Hz. The utterance-level features are computed by averaging the frame-level features.

• frame-level: Google Drive | Baidu Netdisk (password: zb3p)
• utterance-level: Google Drive | Baidu Netdisk (password: qu3u)

All wav files are extracted from the original dataset for diverse downstream tasks. If want to train with standard 5531 utterances for 4 emotions classification, please refer to the iemocap_downstream folder.

Extract features from your dataset

Install from the source code

The minimum environment requirements are python>=3.8 and torch>=1.13. Our testing environments are python=3.8 and torch=2.01.

1. git clone repos.

pip install fairseq
git clone https://github.com/ddlBoJack/emotion2vec.git

2. download emotion2vec checkpoint from:

• Google Drive
• Baidu Netdisk (password: b9fq)
• modelscope: git clone https://www.modelscope.cn/damo/emotion2vec_base.git

3. modify and run scripts/extract_features.sh

Install from FunASR

1. install funasr

pip install -U funasr

2. run the code.

'''
Using the emotion representation model
rec_result only contains {'feats'}
	granularity="utterance": {'feats': [*768]}
	granularity="frame": {feats: [T*768]}
'''

from funasr import AutoModel

model_id = "iic/emotion2vec_base"
model = AutoModel(
    model=model_id,
    hub="ms",  # "ms" or "modelscope" for China mainland users; "hf" or "huggingface" for other overseas users
)

wav_file = f"{model.model_path}/example/test.wav"
rec_result = model.generate(wav_file, output_dir="./outputs", granularity="utterance")
print(rec_result)

The model will be downloaded automatically.

FunASR support file list input in wav.scp (kaldi style):

wav_name1 wav_path1.wav
wav_name2 wav_path2.wav
...

Refer to FunASR for more details.

Training your downstream model

We provide training scripts for IEMOCAP dataset in the iemocap_downstream folder. You can modify the scripts to train your downstream model on other datasets.

Contributors

Citation

If you find our emotion2vec code and paper useful, please kindly cite:

@article{ma2023emotion2vec,
  title={emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation},
  author={Ma, Ziyang and Zheng, Zhisheng and Ye, Jiaxin and Li, Jinchao and Gao, Zhifu and Zhang, Shiliang and Chen, Xie},
  journal={Proc. ACL 2024 Findings},
  year={2024}
}