paper-with-me

Papers

Evaluation of Error and Correlation-Based Loss Functions For Multitask Learning Dimensional Speech Emotion Recognition

2020-03-24 · Bagus Tris Atmaja, Masato Akagi

The choice of a loss function is a critical part in machine learning. This paper evaluated two different loss functions commonly used in regression-task dimensional speech emotion recognition, an error-based and a correlation-based loss functions. We found that using correlation-based loss function with a concordance correlation coefficient (CCC) loss resulted better performance than error-based loss function with a mean squared error (MSE) loss, in terms of the averaged CCC score. The results are consistent with two input feature sets and two datasets. The scatter plots of test prediction by those two loss functions also confirmed the results measured by CCC scores.

📄 PDF Abstract BibTeX arXiv:2003.10724

Code (1)

bagustris/ccc_mse_ser 공식 구현 tf

Tasks

Emotion RecognitionregressionSpeech Emotion Recognition

Similar Papers 제목 키워드 기반

On Multitask Loss Function for Audio Event Detection and Localization

2020-09-11 · Huy Phan, Lam Pham, Philipp Koch, Ngoc Q. K. Duong 외

Audio event localization and detection (SELD) have been commonly tackled using multitask models. Such a model usually consists of a multi-label event classification branch with sigmoid cross-entropy loss for event activi…

Action DetectionActivity DetectionDirection of Arrival EstimationEvent Detection+1

Building Tailored Speech Recognizers for Japanese Speaking Assessment

2025-09-25 · Yotaro Kubo, Richard Sproat, Chihiro Taguchi, Llion Jones arxiv

This paper presents methods for building speech recognizers tailored for Japanese speaking assessment tasks. Specifically, we build a speech recognizer that outputs phonemic labels with accent markers. Although Japanese …

Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation

2024-03-01 · Huaqing Yuan, Yi He, Peng Du, Lu Song

Face images contain a wide variety of attribute information. In this paper, we propose a generalized framework for joint estimation of ordinal and nominal attributes based on information sharing. We tackle the correlatio…

AttributeMulti-Task Learning

Multitask Protein Function Prediction Through Task Dissimilarity

2016-11-03 · Marco Frasca, Nicolò Cesa Bianchi

Automated protein function prediction is a challenging problem with distinctive features, such as the hierarchical organization of protein functions and the scarcity of annotated proteins for most biological functions. W…

PredictionProtein Function Prediction

Implicit biases in multitask and continual learning from a backward error analysis perspective

2023-11-01 · Benoit Dherin

Using backward error analysis, we compute implicit training biases in multitask and continual learning settings for neural networks trained with stochastic gradient descent. In particular, we derive modified losses that …

Continual Learning