Abstract: Controlling text-to-speech (TTS) systems to synthesize speech with the prosodic characteristics expected by users has attracted much attention. To achieve controllability, current studies ...

Abstract: This paper investigates leveraging large-scale speech data to enhance prosodic modeling in speech synthesis, and introduces a model named SP2MC which achieves self-supervised prosody ...

The auditory system is the sensory system for hearing. It consists of the outer ear (the auricle and auditory canal), the middle ear (the tympanic membrane, malleus, incus and stapes), the inner ...