Neural network based end-to-end text to speech (TTS) has significantly improved the quality
of synthesized speech. Prominent methods (eg, Tacotron 2) usually first generate mel …

This paper introduces a new speech corpus called" LibriTTS" designed for text-to-speech
use. It is derived from the original audio and text materials of the LibriSpeech corpus, which …

This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-
TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit …

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech
synthesis model, to learn the latent representation of speaking styles in an unsupervised …

In this paper, we present a robust and effective speech synthesis system that generates
highly natural speech. The key component of proposed system is Duration Informed …

In this work, we propose Flow-TTS, a non-autoregressive end-to-end neural TTS model
based on generative flow. Unlike other non-autoregressive models, Flow-TTS can achieve …

We present the Zero Resource Speech Challenge 2019, which proposes to build a speech
synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without …

Emotional speech synthesis aims to synthesize human voices with various emotional effects.
The current studies are mostly focused on imitating an averaged style belonging to a specific …

Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech
processing and both achieve impressive performance thanks to the recent advance in deep …

In this paper, we present a generic and robust multimodal synthesis system that produces
highly natural speech and facial expression simultaneously. The key component of this …