Article

Recognizing More Emotions with Less Data Using Self-supervised Transfer Learning

2020-08-28

Abstract excerpt

We propose a novel transfer learning method for speech emotion recognition allowing us to obtain promising results when only few training data is available. With as low as 125 examples per emotion class, we were able to reach a higher accuracy than a strong baseline trained on 8 times more data. Our method leverages knowledge contained in pre-trained speech representations extracted from models trained on a more g...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 91529593-2d5b-53f8-8cc8-39851b23dc37
DOI: 10.20944/preprints202008.0645.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Recognizing More Emotions with Less Data Using Self-supervised Transfer LearningDOI 10.20944/preprints202008.0645.v1Read

A Comprehensive Review in Unimodal and Multimodal Emotion RecognitionSemantic proximity Read

Bangla Speech Emotion Recognition Using Deep Learning-Based Ensemble Learning and Feature FusionSemantic proximity Read

HSERNet: Hybrid Speech Emotion Recognition using Conformer-Convolutional Neural NetworksSemantic proximity Read

ArmanEmo: A Persian Dataset for Text-based Emotion DetectionSemantic proximity Read

Facial Affect Detection using Transfer Learning: A Comparative StudySemantic proximity Read

Modelling Human-Like Emotion Perception Using Multimodal Deep LearningSemantic proximity Read

Semantic content outperforms speech prosody in predicting affective experience in naturalistic settingsSemantic proximity Read

Emotion Recognition from Bangla Dialect Speech using Privacy-Aware Deep Learning Models: A Comparative AnalysisSemantic proximity Read

A Hybrid Deep Learning Framework for efficient emotion detection on the facial image datasetSemantic proximity Read

Multimodal modeling of human emotions using sound, image and text fusionSemantic proximity Read

Multi-level Conflict-Aware Network for Multi-modal Sentiment AnalysisSemantic proximity Read

Speech Emotion Recognition using Data Augmentation Method by Cycle-Generative Adversarial NetworksSemantic proximity Read