Talk · International Conference on Applied Artificial Intelligence and Computing · December 17, 2025
Emotion-Aware Speaker Diarization Based on Prosodic and Deep Embedding Integration
Kamoliddin Shukurov, U U Khasanov, Shokhrukhmirzo Kholdorov, Karimova Maftuna, Lutfulla Murodjonov
Abstract
Speaker diarization is the process of identifying speech segments in an audio stream and assigning them to a specific speaker. Since classical systems do not take into account prosodic features, their accuracy decreases in emotional speech situations. In this study, an emotion-sensitive speaker diarization system is proposed. In the model, prosodic vectors derived from prosodic features are combined with the embeddings of the ECAPA-TDNN model in a modulation manner. In the study, the emotion-sensitive speaker diarization model reduced the DER performance of the simple baseline model from 11.6 % to 7.9 %. In addition, it has low computational costs and provides significant results in real-time systems.
More by Shokhrukhmirzo Kholdorov
- A Cache-Aware Compression Framework: Deriving the Compression Target and Stopping Rule for Transformers on CPU-Class HardwareAI · 2026
- SPORTCHILARNING MUSHAK TOLIQISHINI ANIQLASHDA GIBRID XUSUSIYATLAR VA MODIFIKATSIYALANGAN MLP NEYRON TARMOG'INING QO'LLANILISHIBulletin of TUIT Management and Communication Technologies · 2026
- Advanced Speaker Diarization Techniques for Analyzing Uzbek Speech SignalsLecture notes in electrical engineering · 2026 · Citations: 3
- Scientific Foundations for Selecting Spectral Transformation Algorithms in Electromyography Signal ProcessingLecture notes in electrical engineering · 2026 · Citations: 1