Addressing Ambiguity of Emotion Labels Through Meta-learning

by   Takuya Fujioka, et al.

Emotion labels in emotion recognition corpora are highly noisy and ambiguous, due to the annotators' subjective perception of emotions. Such ambiguity may introduce errors in automatic classification and affect the overall performance. We therefore propose a dynamic label correction and sample contribution weight estimation model. Our model is based on a standard BLSTM model with attention with two extra parameters. The first learns a new corrected label distribution, and is aimed to fix the inaccurate labels from the dataset. The other instead estimates the contribution of each sample to the training process, and is aimed to ignore the ambiguous and noisy samples while giving higher weight to the clear ones. We train our model through an alternating optimization method, where in the first epoch we update the neural network parameters, and in the second we keep them fixed to update the label correction and sample importance parameters. When training and evaluating our model on the IEMOCAP dataset, we obtained a weighted accuracy (WA) and unweighted accuracy (UA) of respectively 65.9 absolute improvement of 2.5 attention baseline, trained on the corpus gold labels.


page 1

page 2

page 3

page 4


End-to-end label uncertainty modeling for speech emotion recognition using Bayesian neural networks

Emotions are subjective constructs. Recent end-to-end speech emotion rec...

Embracing Ambiguity: Shifting the Training Target of NLI Models

Natural Language Inference (NLI) datasets contain examples with highly a...

Multi-Classifier Interactive Learning for Ambiguous Speech Emotion Recognition

In recent years, speech emotion recognition technology is of great signi...

Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection

Recent studies on learning with noisy labels have shown remarkable perfo...

Alternating Loss Correction for Preterm-Birth Prediction from EHR Data with Noisy Labels

In this paper we are interested in the prediction of preterm birth based...

Using Crowdsourcing to Train Facial Emotion Machine Learning Models with Ambiguous Labels

Current emotion detection classifiers predict discrete emotions. However...

Multimodal Word Sense Disambiguation in Creative Practice

Language is ambiguous; many terms and expressions can convey the same id...

Please sign up or login with your details

Forgot password? Click here to reset