Skip to main content
padlock icon - secure page this page is secure

Open Access Emotion Recognition in Speech with Latent Discriminative Representations Learning

Download Article:
(PDF 82.3 kb)

This article is Open Access under the terms of the Creative Commons CC BY licence.

Despite significant recent advances in the field of affective computing, learning meaningful representations for emotion recognition remains quite challenging. In this paper, we propose a novel feature learning approach named Latent Discriminative Representation (LDR) learning for speech emotion recognition. Unlike most existing hand-crafted features designed for specific applications or features learnt by a standard neural network, the proposed learning method incorporates an additional training objective in order to learn better representations of the task of interest. To this end, we group the training samples into sets of triplets, satisfying that the second member in each triplet comes from the same class as the first and that the third member comes from a dif ferent class than the first. In the training pr ocess, we maximise the distance of the samples from different classes in the latent representation space, while we minimise the distance for samples from the same class. To evaluate the effectiveness of LDR, we perform extensive experiments on the widely used database IEMOCAP, and find that the LDR improves performance over the standard neural network training procedure.

© 2018 The Author(s). Published by S. Hirzel Verlag · EAA. This is an open access article under the terms of the Creative Commons Attribution (CC BY 4.0) license (

7 References.

No Supplementary Data.
No Article Media
No Metrics

Document Type: Research Article

Publication date: September 1, 2018

This article was made available online on October 10, 2018 as a Fast Track article with title: "Emotion Recognition in Speech with Latent Discriminative Representations Learning".

More about this publication?
  • Acta Acustica united with Acustica, published together with the European Acoustics Association (EAA), is an international, peer-reviewed journal on acoustics. It publishes original articles on all subjects in the field of acoustics, such as general linear acoustics, nonlinear acoustics, macrosonics, flow acoustics, atmospheric sound, underwater sound, ultrasonics, physical acoustics, structural acoustics, noise control, active control, environmental noise, building acoustics, room acoustics, acoustic materials, acoustic signal processing, computational and numerical acoustics, hearing, audiology and psychoacoustics, speech, musical acoustics, electroacoustics, auditory quality of systems. It reports on original scientific research in acoustics and on engineering applications. The journal considers scientific papers, technical and applied papers, book reviews, short communications, doctoral thesis abstracts, etc. In irregular intervals also special issues and review articles are published.
  • Editorial Board
  • Information for Authors
  • Submit a Paper
  • Subscribe to this Title
  • Information for Advertisers
  • Online User License
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more