Emotional Speech Synthesis

DDE’s AI-based emotional text-to-speech (TTS) synthesis technology separates each context from the entire text, analyzes the emotion of each separated context, and automatically tags ± 30 emotional forms. By extracting the characteristics and patterns of emotional forms, our voice waveform recognition model automatically generates a library of emotion models and creates audio files with unique emotional patterns.

Voice Cloning System

Automatically extracting each unique feature from a person’s voice data, DDE’s voice cloning system generates a pattern of each person’s voice colour and reproduces a given sentence or text as an audio file according to each emotional type and selected voice colour.