all AI news
Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations
March 18, 2024, 4:42 a.m. | Debaditya Shome, Ali Etemad
cs.LG updates on arXiv.org arxiv.org
Abstract: We propose EmoDistill, a novel speech emotion recognition (SER) framework that leverages cross-modal knowledge distillation during training to learn strong linguistic and prosodic representations of emotion from speech. During inference, our method only uses a stream of speech signals to perform unimodal SER thus reducing computation overhead and avoiding run-time transcription and prosodic feature extraction errors. During training, our method distills information at both embedding and logit levels from a pair of pre-trained Prosodic and …
abstract arxiv cs.ai cs.cl cs.lg distillation emotion framework inference knowledge learn modal novel recognition speech speech emotion training type
More from arxiv.org / cs.LG updates on arXiv.org
Trainwreck: A damaging adversarial attack on image classifiers
1 day, 11 hours ago |
arxiv.org
Fast Controllable Diffusion Models for Undersampled MRI Reconstruction
1 day, 11 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer
@ GPTZero | Toronto, Canada
Software Engineer III -Full Stack Developer - ModelOps, MLOps
@ JPMorgan Chase & Co. | NY, United States
Senior Lead Software Engineer - Full Stack Senior Developer - ModelOps, MLOps
@ JPMorgan Chase & Co. | NY, United States
Software Engineer III - Full Stack Developer - ModelOps, MLOps
@ JPMorgan Chase & Co. | NY, United States
Research Scientist (m/w/d) - Numerische Simulation Laser-Materie-Wechselwirkung
@ Fraunhofer-Gesellschaft | Freiburg, DE, 79104
Research Scientist, Speech Real-Time Dialog
@ Google | Mountain View, CA, USA