Towards real-time Speech Emotion Recognition using deep neural networks
Open accessAbstract
Most existing Speech Emotion Recognition (SER) systems rely on turn-wise processing, which aims at recognizing emotions from complete utterances and an overly-complicated pipeline marred by many preprocessing steps and hand-engineered features. To overcome both drawbacks, we propose a real-time SER system based on end-to-end deep learning. Namely, a Deep Neural Network (DNN) that recognizes emotions from a one second frame of raw speech spectrograms is presented and investigated. This is achievable due to a deep hierarchical architecture, data augmentation, and sensible regularization. Promising results are reported on two databases which are the eNTERFACE database and the Surrey Audio-Visual Expressed Emotion (SAVEE) database.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Data augmentation to artificially increase the dataset size is used less often than for FER; notable examples include addition of Gaussian noise, different sampling frequencies, and modified playback speed.
“Data augmentation to artificially increase the dataset size is used less often than for FER; notable examples include the addition of Gaussian noise [129], different sampling frequencies [130], and modified playback speed [142].”
From Deep learning for human affect recognition: Insights and new developments (2021) · cites this paper as [130]
The citation lists haven’t been fetched yet
References 25 · Cited by 103
- Authors
- Fayek, H. M., Lech, M., & Cavedon, L.
- Affiliations
- RMIT University (AU)
- Venue
- 2015 9th International Conference on Signal Processing and Communication Systems (ICSPCS)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 1-5
- OpenAlex
- W2281534628
- Cited by
- 103
- References
- 25
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 8 · 2023: 18 · 2022: 14 · 2021: 14 · 2020: 8 · 2019: 13 · 2018: 11 · 2017: 8 · 2016: 3
- FWCI
- 9.78
- Type
- conference paper
- Language
- en
- Open access
- green
- figshare.com
- Licence
- cc-by
- Locations
- International Conference on Signal Processing and Communication Systems (publishedVersion)
- RMIT Research Repository (RMIT University Library) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- Nvidia
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- speech emotion recognition, real-time emotion recognition, end-to-end deep learning, deep neural network, data augmentation, regularization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
