Papers › emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for...

emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition

21 Mar 2024arXiv:2403.14083archive 2025-07-28

Thejan Rajapakshe, Rajib Rana, Sara Khalifa, Berrak Sisman, Bjorn W. Schuller, Carlos Busso

Speech Emotion Recognition (SER) is crucial for enabling computers to understand the emotions conveyed in human communication. With recent advancements in Deep Learning (DL), the performance of SER models has significantly improved. However, designing an optimal DL architecture requires specialised knowledge and experimental assessments. Fortunately, Neural Architecture Search (NAS) provides a potential solution for automatically determining the best DL model. The Differentiable Architecture Search (DARTS) is a particularly efficient method for discovering optimal models. This study presents emoDARTS, a DARTS-optimised joint CNN and Sequential Neural Network (SeqNN: LSTM, RNN) architecture that enhances SER performance. The literature supports the selection of CNN and LSTM coupling to improve performance. While DARTS has previously been used to choose CNN and LSTM operations independently, our technique adds a novel mechanism for selecting CNN and SeqNN operations in conjunction using DARTS. Unlike earlier work, we do not impose limits on the layer order of the CNN. Instead, we let DARTS choose the best layer order inside the DARTS cell. We demonstrate that emoDARTS outperforms conventionally designed CNN-LSTM models and surpasses the best-reported SER results achieved through DARTS on CNN-LSTM by evaluating our approach on the IEMOCAP, MSP-IMPROV, and MSP-Podcast datasets.

PaperPDFCode

Code

jayaneetha/emoDARTS officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Emotion RecognitionNeural Architecture SearchSpeech Emotion Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Emotion Recognition IEMOCAP emoDARTS UA CV 0.7655 #2 of 8 Archive leaderboard report
Speech Emotion Recognition IEMOCAP emoDARTS WA CV 0.7803 #2 of 8 Archive leaderboard report
Speech Emotion Recognition MSP-IMPROV emoDARTS UA .6563 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DARTSLSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections