This paper describes the use of a low-dimensional vector representation of sentence
acoustics to control the output of a feed-forward deep neural network text-to-speech system …

We propose a speech-synthesis model for predicting appropriate voice styles on the basis of
the character-annotated text for audiobook speech synthesis. An audiobook is more …

This paper describes a framework for synthesis of expressive speech based on MARY TTS
and Emotion Markup Language (EmotionML). We describe the creation of expressive unit …

This paper describes the ALISA tool, which implements a lightly supervised method for
sentence-level alignment of speech with imperfect transcripts. Its intended use is to enable …

In this paper, we construct a Japanese audiobook speech corpus called" J-MAC" for speech
synthesis research. With the success of reading-style speech synthesis, the research target …

Creating new voices for a TTS system often requires a costly procedure of designing and
recording an audio corpus, a time consuming and effort intensive task. Using publicly …

Narrative aesthetic absorption describes a state in which we focus on the story world of a
narrative while becoming less aware of our surroundings and ourselves. It is characterized …

During the last decades, the majority of works devoted on expressive speech acoustic
analysis have focused on emotions, although there is a growing interest in other speaking …

Nowadays, especially with the upswing of neural networks, speech synthesis is almost
totally data driven. The goal of this thesis is to provide methods for automatic and …

This paper introduces a method for lightly supervised discriminative training using MMI to
improve the alignment of speech and text data for use in training HMM-based TTS systems …