Learning Discriminative features using Center Loss and Reconstruction as Regularizer for Speech Emotion Recognition

2019-06-19 · Suraj Tripathi, Abhiram Ramesh, Abhay Kumar, Chirag Singh, Promod Yenigalla

This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the recognition of emotion in speech. Speech features such as Spectrograms and Mel-frequency Cepstral Coefficient s (MFCCs) help retain emotion-related low-level characteristics in speech. We experimented with several Deep Neural Network (DNN) architectures that take in speech features as input and trained them under both softmax and center loss, which resulted in highly discriminative features ideal for Speech Emotion Recognition (SER). Our networks also employ a regularizing effect by simultaneously performing the auxiliary task of reconstructing the input speech features. This sharing of representations among related tasks enables our network to better generalize the original task of SER. Some of our proposed networks contain far fewer parameters when compared to state-of-the-art architectures.

📄 PDF Abstract BibTeX arXiv:1906.08873

Code (0)

등록된 구현이 없습니다.

Tasks

Emotion Recognition Metric Learning Speech Emotion Recognition

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Triplet-Center Loss for Multi-View 3D Object Retrieval

2018-03-16 · CVPR 2018 6 · Xinwei He, Yang Zhou, Zhichao Zhou, Song Bai 외

Most existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with …

3D Object Recognition 3D Object Retrieval 3D Shape Classification 3D Shape Retrieval+6

learning discriminative features from spectrograms using center loss for speech emotion recognition

2025-01-02 · Dongyang Dai, Zhiyong Wu, Runnan Li, Xixin Wu 외

Identifying the emotional state from speech is essential for the natural interaction of the machine with the speaker. However, extracting effective features for emotion recognition is difficult, as emotions are ambiguous…

Emotion Recognition Speech Emotion Recognition

Adaptive Neuron-wise Discriminant Criterion and Adaptive Center Loss at Hidden Layer for Deep Convolutional Neural Network

2020-04-17 · Motoshi Abe, Junichi Miyao, Takio Kurita

A deep convolutional neural network (CNN) has been widely used in image classification and gives better classification accuracy than the other techniques. The softmax cross-entropy loss function is often used for classif…

Face Recognition General Classification image-classification Image Classification

Improving Adversarial Robustness by Encouraging Discriminative Features

2018-11-01 · Chirag Agarwal, Anh Nguyen, Dan Schonfeld

Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted …

Adversarial Robustness

A Discriminative Feature Learning Approach for Deep Face Recognition

2016-09-16 · ECCV 2016 2016 9 · Yandong Wen, Kaipeng Zhang, Zhifeng Li, Yu Qiao

Convolutional neural networks (CNNs) have been widely used in computer vision community, significantly improving the state-ofthe-art. In most of the available CNNs, the softmax loss function is used as the supervision si…

Face Recognition Face Verification