Pronouncing Hard Words: Phoneme Adaptation of a Pretrained Conversational Text to Speech Model

Yashish M. Siriwardena, Dinesh K. Gnanasekaran, Tanmay Laud +3

Voice agents built as cascaded automatic speech recognition (ASR)->large language model (LLM)-> text-to-speech (TTS) pipelines increasingly rely on conversational TTS: streaming, c…