EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech

arXiv:2403.08164v1 Announce Type: cross
Abstract: Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used. However, training a TTS model which includes RNN components requires powerful GPU performance and takes a long time. In contrast, CNN-based sequence synthesis techniques can significantly reduce the parameters and training time of a TTS model while guaranteeing a certain performance due to their …

abstract arxiv become components cs.lg cs.sd data deep learning eess.as gpu however low modeling networks neural networks performance quality recurrent neural networks results rnn speech standard synthesis systems text text-to-speech training tts type