Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation

arXiv:2404.02592v1 Announce Type: new
Abstract: Contemporary neural speech synthesis models have indeed demonstrated remarkable proficiency in synthetic speech generation as they have attained a level of quality comparable to that of human-produced speech. Nevertheless, it is important to note that these achievements have predominantly been verified within the context of high-resource languages such as English. Furthermore, the Tacotron and FastSpeech variants show substantial pausing errors when applied to the Korean language, which affects speech perception and naturalness. In order to …

abstract arxiv cs.cl cs.sd eess.as human indeed quality speech speech generation synthesis synthetic synthetic speech tts type