Shadowgraph
TrendingAbout
Sign in
← Explore by area

Speech Emotion Recognition

7 repos

Speech emotion recognition (SER) systems that detect and classify emotional states—valence, arousal, dominance, and categorical emotions—from audio signals. The cluster centers on WavLM-based models trained on the MSP-Podcast corpus, a primary benchmark dataset for emotion recognition research. Repositories here implement baseline models, fine-tuned variants for multiple languages, and evaluation frameworks for predicting emotional dimensions from spoken language.

Jupyter Notebook · 2
Python · 2
speech-emotion-recognition ·569
wav2vec2 ·567
deep-learning ·564
transformer-models ·564
dominance ·562
msp-podcast ·562
onnx ·562
arousal ·562
valence ·562
audio-classification ·7

Related clusters

Cluster 63767739Fine-tuned Large Language Models28Cluster 6539058Cluster 6539038Cluster 6567147Cluster 63523427

CAiRE/SER-wav2vec2-large-xlsr-53-eng-zho-adults

Model

Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition

0

4 commits

CAiRE/SER-wav2vec2-large-xlsr-53-eng-zho-all-age

Model

Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition

4

7 commits

CAiRE/SER-wav2vec2-large-xlsr-53-eng-zho-elderly

Model

Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition

0

4 commits

viksit-siddhant/compare2023

SER and audio classification using both a Wav2Vec2 based model and an ASR->Bert pipeline, as well…

Python

1

4 commits

vmehtacode/speech-emotion-recognition

Deep learning system for emotion recognition from speech, achieving 50.5% accuracy on 8-class…

Python

2

29 commits

audeering/w2v2-how-to

How to use our public wav2vec2 dimensional emotion model

Jupyter Notebook

562

16 commits

HLTCHKUST/elderly_ser

Transferability of cross-lingual and cross-age speech emotion recognition

Jupyter Notebook

21

37 commits