Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off‐line applications, novel tools can alter the role of an animator to that of a director, who provides only high‐level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning‐based motion synthesis method called MoGlow, we propose a new generative model for generating state‐of‐the‐art realistic speech‐driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper‐body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full‐body gesticulation, including the synthesis of stepping motion and stance.

No abstract

Speech synthesis applications have become an ubiquity, in navigation systems, digital assistants or as screen or audio book readers. Despite their impact on the acceptability of the systems in which they are embedded, and despite the fact that different applications probably need different types of TTS voices, TTS evaluation is still largely treated as an isolated problem. Even though there is strong agreement among researchers that the mainstream approaches to Text-to-Speech (TTS) evaluation are often insufficient and may even be misleading, there exist few clear-cut suggestions as to (1) how TTS evaluations may be realistically improved on a large scale, and (2) how such improvements may lead to an informed feedback for system developers and, ultimately, better systems relying on TTS. This paper reviews the current state-of-the-art in TTS evaluation, and suggests a novel user-centered research program for this area.

In this paper, we present Furhat — a back-projected human-like robot head using state-of-the art facial animation. Three experiments are presented where we investigate how the head might facilitate human–robot face-to-face interaction. First, we investigate how the animated lips increase the intelligibility of the spoken output, and compare this to an animated agent presented on a flat screen, as well as to a human face. Second, we investigate the accuracy of the perception of Furhat's gaze in a setting typical for situated interaction, where Furhat and a human are sitting around a table. The accuracy of the perception of Furhat's gaze is measured depending on eye design, head movement and viewing angle. Third, we investigate the turn-taking accuracy of Furhat in a multi-party interactive setting, as compared to an animated agent on a flat screen. We conclude with some observations from a public setting at a museum, where Furhat interacted with thousands of visitors in a multi-party interaction.

Synthesising spontaneous speech is a difficult task due to disfluencies, high variability and syntactic conventions different from those of written language. Using found data, as opposed to labrecorded conversations, for speech synthesis adds to these challenges because of overlapping speech and the lack of control over recording conditions. In this paper we address these challenges by using a speaker-dependent CNN-LSTM breath detector to separate continuous recordings into utterances, which we here apply to extract nine hours of clean single-speaker breath groups from a conversational podcast. The resulting corpus is transcribed automatically (both lexical items and filler tokens) and used to build several voices on a Tacotron 2 architecture. Listening tests show: i) pronunciation accuracy improved with phonetic input and transfer learning; ii) it is possible to create a more fluent conversational voice by training on data without filled pauses; and iii) the presence of filled pauses improved perceived speaker authenticity. Another listening test showed the found podcast voice to be more appropriate for prompts from both public speeches and casual conversations, compared to synthesis from found read speech and from a manually transcribed lab-recorded spontaneous conversation.