While speaker adaptation for end-to-end speech synthesis using speaker embeddings can
produce good speaker similarity for speakers seen during training, there remains a gap for …

This paper introduces a new multi-speaker English dataset for training text-to-speech
models. The dataset is based on LibriVox audiobooks and Project Gutenberg texts, both in …

On account of growing demands for personalization, the need for a so-called few-shot TTS
system that clones speakers with only a few data is emerging. To address this issue, we …

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent
years. However, accessing and controlling speech attributes such as speaker identity …

Recent advancements in deep learning led to human-level performance in single-speaker
speech synthesis. However, there are still limitations in terms of speech quality when …

Recently, sequence-to-sequence models with attention have been successfully applied in
Text-to-speech (TTS). These models can generate near-human speech with a large …

Previous work on speaker adaptation for end-to-end speech synthesis still falls short in
speaker similarity. We investigate an orthogonal approach to the current speaker adaptation …

Deep neural network (DNN)-based systems generally require large amounts of training
data, so they have data scarcity problems in low-resource languages. Recent studies have …

In this paper, we propose a framework for environmental sound synthesis from
onomatopoeic words. As one way of expressing an environmental sound, we can use an …

End-to-end TTS advancement has shown that synthesized speech prosody can be
controlled by conditioning the decoder with speech prosody attribute labels. However, to …