InterActor: Speech-Driven Embodied Interactive Actor

Watanabe, Tetsu; Okubo, Masashi; Nakashige, Mutsuhiro; Danbara, Ryusei

doi:10.1201/9780429187735-4

Search citation statements

Order By: Relevance

Paper Sections

Select...

Speech-driven Embodied Interaction System1

Previous Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2020

Publication Types

Select...

Article1

Book1

Relationship

Self Cite1

Independent1

Authors

Journals

Cited by 2 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the analysis results of the embodied virtual communication system, focusing on embodied rhythms such as nodding and gestures, the speech-driven embodied system with embodied CG character InterActor or the physical interaction robot InterRobot which automatically generates the communicative motions and actions as the speaker and the listener has been developed (Watanabe et al, 2004b).…”

Section: Speech-driven Embodied Interaction Systemmentioning

confidence: 99%

Human-entrained embodied interaction and communication technology for human-connected IoT design

Watanabe

2020

JAMDSM

Self Cite

View full text Add to dashboard Cite

Section: Speech-driven Embodied Interaction Systemmentioning

confidence: 99%

Human-entrained embodied interaction and communication technology for human-connected IoT design

Watanabe

2020

JAMDSM

Self Cite

View full text Add to dashboard Cite

“…Cassel et al [6] report a comprehensive rule-based model that triggers backchannels from multi-modal input. Watanabe et al [30] describe a rule-based speech driven interactive agent. Nishimura et al [26] presented a decision tree model driven by prosodic audio features.…”

Section: Previous Workmentioning

confidence: 99%

Predicting Head Pose in Dyadic Conversation

Greenwood

Laycock

Matthews

2017

Intelligent Virtual Agents

View full text Add to dashboard Cite

Natural movement plays a significant role in realistic speech animation. Numerous studies have demonstrated the contribution visual cues make to the degree we, as human observers, find an animation acceptable. Rigid head motion is one visual mode that universally co-occurs with speech, and so it is a reasonable strategy to seek features from the speech mode to predict the head pose. Several previous authors have shown that prediction is possible, but experiments are typically confined to rigidly produced dialogue. Expressive, emotive and prosodic speech exhibit motion patterns that are far more difficult to predict with considerable variation in expected head pose. People involved in dyadic conversation adapt speech and head motion in response to the others’ speech and head motion. Using Deep Bi-Directional Long Short Term Memory (BLSTM) neural networks, we demonstrate that it is possible to predict not just the head motion of the speaker, but also the head motion of the listener from the speech signal

show abstract

InterActor: Speech-Driven Embodied Interactive Actor

Cited by 2 publications

References 1 publication

Human-entrained embodied interaction and communication technology for human-connected IoT design

Human-entrained embodied interaction and communication technology for human-connected IoT design

Predicting Head Pose in Dyadic Conversation

Contact Info

Product

Resources

About