Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural
speech given text, is a hot research topic in speech, language, and machine learning …

Recently, neural network based speech synthesis has achieved outstanding results, by
which the synthesized audios are of excellent quality and naturalness. However, current …

We describe a sequence-to-sequence neural network which directly generates speech
waveforms from text inputs. The architecture extends the Tacotron model by incorporating a …

We present a novel generative model that combines state-of-the-art neural text-to-speech
(TTS) with semi-supervised probabilistic latent variable models. By providing partial …

Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded
in generating human-like speech, there is still room for improvements to its naturalness and …

In this paper we propose Flowtron: an autoregressive flow-based generative network for text-
to-speech synthesis with control over speech variation and style transfer. Flowtron borrows …

Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable
from natural speech. However, the prosody of generated utterances often represents the …

This paper describes the Microsoft end-to-end neural text to speech (TTS) system:
DelightfulTTS for Blizzard Challenge 2021. The goal of this challenge is to synthesize …

Speech synthesis, also known as text-to-speech (TTS), has attracted increasingly more
attention. Recent advances on speech synthesis are overwhelmingly contributed by deep …

We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS)
system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in …