Speech emotion recognition (SER) datasets for 70 languages and a benchmark of 11 speech models (HuBERT, wav2vec 2.0, WavLM, Whisper) in 29 languages. Interspeech 2026.
benchmark audio-classification whisper speech-processing affective-computing ser emotion-detection emotion-recognition emotion-classification speech-emotion-recognition interspeech self-supervised-learning low-resource-languages emotional-speech hubert wav2vec2 wavlm multilingual-emotion-recognition speech-datasets kuralnet
-
Updated
Oct 31, 2026 - Python