Deep Architecture Enhancing Robustness to Noise, Adversarial Attacks, and Cross-corpus Setting for Speech Emotion Recognition
Paper
Paper/Presentation Title | Deep Architecture Enhancing Robustness to Noise, Adversarial Attacks, and Cross-corpus Setting for Speech Emotion Recognition |
---|---|
Presentation Type | Paper |
Authors | Latif, Siddique (Author), Rana, Rajib (Author), Khalifa, Sara (Author), Jurdak, Raja (Author) and Schuller, Bjorn W. (Author) |
Journal or Proceedings Title | Proceedings of the 21st Annual Conference of the International Speech Communication Association (INTERSPEECH 2020) |
Journal Citation | 4, pp. 2327-2331 |
Number of Pages | 5 |
Year | 2020 |
Place of Publication | France |
ISBN | 9781713820697 |
Digital Object Identifier (DOI) | https://doi.org/10.21437/Interspeech.2020-3190 |
Web Address (URL) of Paper | https://www.isca-speech.org/archive/interspeech_2020/latif20b_interspeech.html |
Conference/Event | 21st Annual Conference of the International Speech Communication Association: Cognitive Intelligence for Speech Processing (INTERSPEECH 2020) |
Event Details | Rank A A A A A A A |
Event Details | 21st Annual Conference of the International Speech Communication Association: Cognitive Intelligence for Speech
Processing (INTERSPEECH 2020) Event Date 25 to end of 29 Oct 2020 Event Location Shanghai, China |
Abstract | Speech emotion recognition systems (SER) can achieve high accuracy when the training and test data are identically distributed, but this assumption is frequently violated in practice and the performance of SER systems plummet against unforeseen data shifts. The design of robust models for accurate SER is challenging, which limits its use in practical applications. In this paper we propose a deeper neural network architecture wherein we fuse Dense Convolutional Network (DenseNet), Long short-term memory (LSTM) and Highway Network to learn powerful discriminative features which are robust to noise. We also propose data augmentation with our network architecture to further improve the robustness. We comprehensively evaluate the architecture coupled with data augmentation against (1) noise, (2) adversarial attacks and (3) cross-corpus settings. Our evaluations on the widely used IEMOCAP and MSP-IMPROV datasets show promising results when compared with existing studies and state-of-the-art models. |
Keywords | speech emotion, mixup, data augmentation, convolutional neural networks, DenseNet, highway network. |
Related Output | |
Is part of | Deep Representation Learning for Speech Emotion Recognition |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 460212. Speech recognition |
460206. Knowledge representation and reasoning | |
460208. Natural language processing | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
This article is part of a UniSQ Thesis by publication. See Related Output. | |
Byline Affiliations | Institute for Resilient Regions |
University of New South Wales | |
Queensland University of Technology | |
Imperial College London, United Kingdom | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q63yq/deep-architecture-enhancing-robustness-to-noise-adversarial-attacks-and-cross-corpus-setting-for-speech-emotion-recognition
119
total views12
total downloads5
views this month0
downloads this month