This portal serves as a continuous evaluation platform for Speech Emotion Recognition (SER) systems. Researchers and developers are invited to submit their models and compare performance using a standardized benchmark based on the MSP-Podcast corpus. The dataset contains speech segments from audio-sharing platforms, annotated by multiple raters using both categorical emotions and continuous emotional attributes.
Participants can evaluate their models on the following tasks:
Access to the MSP-Podcast corpus requires signing the academic license agreement (Don't forget to sign at the end of third page). Interested users should email the signed agreement to msp-lab@utdallas.edu.
Participants may use standard pre-trained models such as wav2vec2.0, HuBERT, and other general-purpose self-supervised models. However, using models pre-trained on emotion-specific datasets is not allowed. To ensure comparability, training should be limited to the MSP-Podcast corpus only.
Submissions must follow the required CSV format and should be uploaded via the submission portal. Once submitted, results will appear on the public leaderboard.
Submissions are automatically evaluated based on standard SER metrics. For categorical tasks, accuracy and F1-score are reported. For emotional attributes, Concordance Correlation Coefficient (CCC) is used for evaluation.
This platform is open year-round to promote ongoing progress and transparent comparison in speech emotion recognition research.
Before submission, please read and follow the instructions carefully.
Only registered team submissions will be accepts. To register please visit the
overview tab.
For information about Interspeech 2025 challenge baselines visit this link.
Each registered email is permitted a maximum of one submission per two weeks per task. For the first submission, participants may choose any preferred team name. However, it is important to use the same team name for subsequent submissions, as any different name will result in rejection.
The submission portal is open year-round.
FileName, EmoClass
MSP-PODCAST_test3_0001.wav, S
MSP-PODCAST_test3_0002.wav, D
MSP-PODCAST_test3_0003.wav, A
MSP-PODCAST_test3_0004.wav, U
...
FileName, EmoAct, EmoVal, EmoDom
MSP-PODCAST_test3_0001.wav, 5.962445394, 1.645595285, 3.277091995
MSP-PODCAST_test3_0002.wav, 5.925202743, 3.510046627, 4.902689017
MSP-PODCAST_test3_0003.wav, 5.133939009, 2.012986747, 5.79230556
MSP-PODCAST_test3_0004.wav, 2.727285967, 4.033873751, 1.566529833
...