ISCA Archive Interspeech 2025
ISCA Archive Interspeech 2025

The Interspeech 2025 Challenge on Speech Emotion Recognition in Naturalistic Conditions

Abinay Reddy Naini, Lucas Goncalves, Ali N. Salman, Pravin Mote, Ismail R. Ulgen, Thomas Thebaud, Laureano Moro Velazquez, Leibny Paola Garcia, Najim Dehak, Berrak Sisman, Carlos Busso

The Speech Emotion Recognition in Naturalistic Conditions Challenge, part of Interspeech 2025, builds on previous efforts to advance Speech Emotion Recognition (SER) in real-world scenarios. The focus is on recognizing emotions from spontaneous speech, moving beyond controlled datasets. It provides a framework for speaker-independent training, development, and evaluation, with annotations for both categorical and dimensional tasks. The challenge attracted a record number of participants, significantly increasing submissions and benchmarking performances, leading to state-of-the-art results. This paper summarizes key outcomes, analyzing top-performing methods, emerging trends, and innovative directions. We highlight the effectiveness of combining audio and text-based foundational models to achieve robust SER systems. The competition website, with leaderboards, baseline code, and instructions, is available at: \url{https://lab-msp.com/MSP-Podcast_Competition/IS2025/}.