An official website of the United States government
Abstract Gestures that accompany speech are an essential part of natural and efficient embodied human communication. The automatic generation of such co‐speech gestures is a long‐standing problem in computer animation and is considered an enabling technology for creating believable characters in film, games, and virtual social spaces, as well as for interaction with social robots. The problem is made challenging by the idiosyncratic and non‐periodic nature of human co‐speech gesture motion, and by the great diversity of communicative functions that gestures encompass. The field of gesture generation has seen surging interest in the last few years, owing to the emergence of more and larger datasets of human gesture motion, combined with strides in deep‐learning‐based generative models that benefit from the growing availability of data. This review article summarizes co‐speech gesture generation research, with a particular focus on deep generative models. First, we articulate the theory describing human gesticulation and how it complements speech. Next, we briefly discuss rule‐based and classical statistical gesture synthesis, before delving into deep learning approaches. We employ the choice of input modalities as an organizing principle, examining systems that generate gestures from audio, text and non‐linguistic input. Concurrent with the exposition of deep learning approaches, we chronicle the evolution of the related training data sets in terms of size, diversity, motion quality, and collection method (e.g., optical motion capture or pose estimation from video). Finally, we identify key research challenges in gesture generation, including data availability and quality; producing human‐like motion; grounding the gesture in the co‐occurring speech in interaction with other speakers, and in the environment; performing gesture evaluation; and integration of gesture synthesis into applications. We highlight recent approaches to tackling the various key challenges, as well as the limitations of these approaches, and point toward areas of future development.
more »
« less
COMPARING MANUAL VS. SEMI-AUTOMATED METHODS FOR THE CODING OF CO-SPEECH GESTURES
While motion capture is rapidly becoming the gold standard for research on the intricacies of co-speech gesture and its relationship to speech, traditional marker-based motion capture technology is not always feasible, meaning researchers must code video data manually. We compare two methods for coding co-speech gestures of the hands and arms in video data of spontaneous speech: manual coding and semi-automated coding using OpenPose, a markerless motion capture software. We provide a comparison of the temporal alignment of gesture apexes based on video recordings of interviews with speakers of Medumba (Grassfields Bantu). Our results show a close correlation between the computationally calculated apexes and our hand-annotated apexes, suggesting that both methods are equally valid for coding video data. The use of markerless motion capture technology for gesture coding will enable more rapid coding of manual gestures, while still allowing
more »
« less
- Award ID(s):
- 2306149
- PAR ID:
- 10451414
- Editor(s):
- Skarnitzl, R. &
- Date Published:
- Journal Name:
- Proceedings of the International Congress of Phonetic Sciences
- ISSN:
- 0301-3162
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Co-speech gestures are timed to occur with prosodically prominent syllables in several languages. In prior work in Indo-European languages, gestures are found to be attracted to stressed syllables, with gesture apexes preferentially aligning with syllables bearing higher and more dynamic pitch accents. Little research has examined the temporal alignment of co-speech gestures in African tonal languages, where metrical prominence is often hard to identify due to a lack of canonical stress correlates, and where a key function of pitch is in distinguishing between words, rather than marking intonational prominence. Here, we examine the alignment of co-speech gestures in two different Niger-Congo languages with very different word structures, Medʉmba (Grassfields Bantu, Cameroon) and Igbo (Igboid, Nigeria). Our findings suggest that the initial position in the stem tends to attract gestures in Medʉmba, while the final syllable in the word is the default position for gesture alignment in Igbo; phrase position also influences gesture alignment, but in language-specific ways. Though neither language showed strong evidence of elevated prominence of any individual tone value, gesture patterning in Igbo suggests that metrical structure at the level of the tonal foot is relevant to the speech-gesture relationship. Our results demonstrate how the speech-gesture relationship can be a window into patterns of word- and phrase-level prosody cross-linguistically. They also show that the relationship between gesture and tone (and the related notion of ‘tonal prominence’) is mediated by tone’s function in a language.more » « less
-
Humans rarely speak without producing co-speech gestures of the hands, head, and other parts of the body. Co-speech gestures are also highly restricted in how they are timed with speech, typically synchronizing with prosodically-prominent syllables. What functional principles underlie this relationship? Here, we examine how the production of co-speech manual gestures influences spatiotemporal patterns of the oral articulators during speech production. We provide novel evidence that words uttered with accompanying co-speech gestures are produced with more extreme tongue and jaw displacement, and that presence of a co-speech gesture contributes to greater temporal stability of oral articulatory movements. This effect–which we term coupling enhancement–differs from stress-based hyperarticulation in that differences in articulatory magnitude are not vowel-specific in their patterning. Speech and gesture synergies therefore constitute an independent variable to consider when modeling the effects of prosodic prominence on articulatory patterns. Our results are consistent with work in language acquisition and speech-motor control suggesting that synchronizing speech to gesture can entrain acoustic prominence.more » « less
-
Skarnitzl, R. & (Ed.)The timing of both manual co-speech gestures and head gestures is sensitive to prosodic structure of speech. However, head gesters are used not only by speakers, but also by listeners as a backchanneling device. Little research exists on the timing of gestures in back-channeling. To address this gap, we compare timing of listener and speaker head gestures in an interview context. Results reveal the dual role that head gestures play in speech and conversational interaction: while they are coordinated in key ways to one’s own speech, they are also coordinated to the gestures (and hence, the speech) of a conversation partner when one is actively listening to them. We also show that head gesture timing is sensitive to social dynamics between interlocutors. This study provides a novel contribution to literature on head gesture timing and has implications for studies of discourse and accommodation.more » « less
-
Abstract As artificial intelligence and industrial automation are developing, human–robot collaboration (HRC) with advanced interaction capabilities has become an increasingly significant area of research. In this paper, we design and develop a real-time, multi-model HRC system using speech and gestures. A set of 16 dynamic gestures is designed for communication from a human to an industrial robot. A data set of dynamic gestures is designed and constructed, and it will be shared with the community. A convolutional neural network is developed to recognize the dynamic gestures in real time using the motion history image and deep learning methods. An improved open-source speech recognizer is used for real-time speech recognition of the human worker. An integration strategy is proposed to integrate the gesture and speech recognition results, and a software interface is designed for system visualization. A multi-threading architecture is constructed for simultaneously operating multiple tasks, including gesture and speech data collection and recognition, data integration, robot control, and software interface operation. The various methods and algorithms are integrated to develop the HRC system, with a platform constructed to demonstrate the system performance. The experimental results validate the feasibility and effectiveness of the proposed algorithms and the HRC system.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
