LEARNING DEVICE AND DEVICE FOR SPEAKING RATE CONTROLLABLE TEXT-TO-SPEECH

摘要

According to an embodiment of the present invention, according to an embodiment of the present invention, there is provided a text-to-speech learning apparatus capable of controlling a speech speed, including at least one processor, wherein the at least one processor includes text and speed information receives input and generates first output voice data using a text-to-speech (TTS) model, and voice data that is paired with the generated first output voice data and the text stored in a voice database is used to update the text-to-speech (TTS) model.