An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era
It addresses the problem of making synthetic speech more engaging and natural for applications in human-computer interaction, but it is an incremental overview rather than a novel contribution.
This paper reviews the challenge of adding emotional expressivity to synthetic speech, which is crucial for natural human-computer interaction, and outlines current trends and state-of-the-art deep learning methods in affective speech synthesis and conversion.
Speech is the fundamental mode of human communication, and its synthesis has long been a core priority in human-computer interaction research. In recent years, machines have managed to master the art of generating speech that is understandable by humans. But the linguistic content of an utterance encompasses only a part of its meaning. Affect, or expressivity, has the capacity to turn speech into a medium capable of conveying intimate thoughts, feelings, and emotions -- aspects that are essential for engaging and naturalistic interpersonal communication. While the goal of imparting expressivity to synthesised utterances has so far remained elusive, following recent advances in text-to-speech synthesis, a paradigm shift is well under way in the fields of affective speech synthesis and conversion as well. Deep learning, as the technology which underlies most of the recent advances in artificial intelligence, is spearheading these efforts. In the present overview, we outline ongoing trends and summarise state-of-the-art approaches in an attempt to provide a comprehensive overview of this exciting field.