Top Text-to-Speech Models of 2026: Proprietary vs Open Source Compared

Open source TTS models Kokoro, Orpheus, and Piper are tested on symbols, abbreviations, and prosody with CER and MOS results.
IEEE

Speech Emotional Recognition using XGBoost and Deep Learning Algorithm and Multisource Datasets

Abstract: Speech emotional recognition (SER) focuses on developing computers' comprehension and response to human emotional tones and is a key field of research in human-machine interaction. This ...
IEEE

M 4 SER: Multimodal, Multirepresentation, Multitask, and Multistrategy Learning for Speech Emotion Recognition

Abstract: Multimodal speech emotion recognition (SER) has emerged as pivotal for improving human–machine interaction. Researchers are increasingly leveraging both speech and textual information ...