1,354,049 research outputs found
A GAN-based Approach for Generating Culture-Aware Co-Speech Gestures
No full textEmbedding social robots with the capability of accompanying their sentences with natural gestures may be the key to increasing their acceptability and their usage in real contexts. However, it could be argued that the definition of natural communicative gestures is not trivial, since it strictly depends on the culture of the person interacting with the robot. The proposed work investigates the usage of Generative Adversarial Networks (GANs) for generating culture-dependent communicative gestures based on speech audio features. To this aim, a custom dataset, only composed of persons belonging to the same culture, has been created, to extract all keypoints and audio features needed to train the network. Then, a generative model, also consisting of a voice conversion module, has been implemented and tested with the humanoid robot Pepper. Preliminary results, obtained through objective measurements and subjective evaluation, show that the proposed approach may be promising for generating culture-dependent communicative gestures for social robots
Towards Culture-Aware Co-Speech Gestures for Social Robots
No full textEmbedding social robots with the capability of accompanying their sentences with natural gestures may be the key to increasing their acceptability and their usage in real contexts. However, the definition of natural communicative gestures may not be trivial, since it strictly depends on the culture of the person interacting with the robot. The proposed work investigates the possibility of generating culture-dependent communicative gestures, by proposing an integrated approach based on a custom dataset composed exclusively of persons belonging to the same culture, an adversarial generation module based on speech audio features, a voice conversion module to manage the multi-person dataset, and a 2D-to-3D mapping module for generating three-dimensional gestures. The approach has eventually been implemented and tested with the humanoid robot Pepper. Preliminary results, obtained through a statistical analysis of the evaluations made by human participants identifying themselves as belonging to different cultures, are discussed
Multimodal Culture-Aware Gesture Generation for Social Robots: Combining Semantic Similarity with Generative Models
No full textAs social robots become integrated into daily life, optimizing their interactions with humans is crucial to enhancing their acceptance. Cultural differences significantly influence verbal and non-verbal human-robot communication, yet embedding culturally adaptive behaviors, such as co-speech gestures, remains largely unexplored. This thesis addresses the challenge of generating culture-aware co-speech gestures for social robots by introducing two novel approaches: a rule-based method leveraging semantic similarity scores and a data-driven model utilizing hierarchical diffusion transformers. Both approaches are designed to be computationally efficient and capable of generating gestures in real time, making them practical for social robots with limited computational resources. Furthermore, we consider only upper-body movements, which can be easily reproduced by humanoid robots with minimal or no hand movement, ensuring broader applicability across different robotic platforms.
The rule-based approach employs algorithms to identify contextually relevant words associated with Symbolic and Deictic gestures within sentences. Three algorithms are proposed: one compares sentences that heuristically represent the context in which a set of gestures are produced with a fixed number of words in the objective sentence, another allows for a variable number of words, and a third relies on a statistical analysis of participant-labeled sentences without using semantic similarity scores. Evaluation using Average Precision (AP), Intersection Over Union (IOU), and Average Computational Time (ACT), demonstrates that the semantic-based algorithms outperform the statistics-based algorithm, with the variable-word approach achieving the highest performance despite increased computational demands.
The data-driven model, designed to map multimodal speech features to gestures while incorporating cultural components, employs an autoregressive architecture using hierarchical diffusion transformers.
It generates four seconds of motion-related encodings from noisy motion, audio, text, cultural embeddings, and one second of previous motion context. The motion encodings are eventually decoded using a pre-trained vector-quantized variational autoencoder. The model leverages two multi-head attention blocks to capture relationships within motion features and between motion and low-level audio features (e.g., rhythm and emphasis). Additionally, adaptive instance normalization layers condition the motion style on speech semantics and cultural context. Preliminary objective results indicate that the model produces realistic, culturally adaptive co-speech gestures in real-time using the various inputs.
To efficiently embed cultural components and better understand the impact of culture on data, extensive studies were conducted across multimodal datasets, beginning with publicly available resources and progressing to a custom-built dataset. High-level analysis of the existing LISI-HHI multimodal interaction dataset revealed cultural differences in textual and gestural features. Culture classification using Fully Connected Neural Networks (FCNNs) and Random Forest (RF) models achieved high accuracy with subject-dependent data splits but struggled to generalize to unseen speakers in subject-independent splits. Although adversarial learning improved speaker-invariant representation to some extent, the dataset’s limited speaker count constrained further generalization.
To overcome these limitations, the TED4C-L dataset was developed, comprising 737 speakers from four distinct cultures, extracted from YouTube TED Talks. TED4C-L offers a diverse, speaker-balanced, and multilingual collection that facilitates enhanced cultural representation learning. A similar analysis to that conducted on the LISI-HHI dataset applied to TED4C-L revealed significant improvements in classification accuracy. Subject-independent cultural representations derived from TED4C-L were subsequently embedded into the data-driven model to enhance its performance.
Together, these efforts contribute to a robust framework for generating culture-aware co-speech gestures, paving the way for more effective and culturally adaptive human-robot interactions
Culture Awareness in Intelligent Systems
No full textUnderstanding how the data used to train intelligent systems affects their behaviour is a critical task in the Artificial Intelligence field. It is also known that making artificial agents capable of adapting their actions according to the culture improves their interaction with humans. For this reason, it may be crucial to know how the cultural component inside data affects the prediction of intelligent systems. In this paper, we propose a method to acknowledge the cultural factor inside data, and we show some preliminary results obtained by using Random Forest and Support Vector Machine models on two publicly available datasets
Going Beyond Counting First Authors in Author Co-citation Analysis
No full textThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
No full text“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
No full textWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
No full textWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
Author, publisher and bookseller : a tripartite synergy in Nigerian book industry
No full textThis work is about the roles of Author, Publisher and Bookseller in Book development in
Nigeria. The paper started by delving into the history of Book Publishing in Nigeria after
which it proceeded by defining who an author, a publisher, and a bookseller is and
expatiated on the indispensable roles of these key actors in Nigerian Book Industry and in
the emerging Information Society. Furthermore, the various constraints to book
development were identified while the paper advised on how the Book Industry can be
further promoted in Nigeria. However, the paper concluded and made recommendations
on how the Book sector can help in enhancing scholarship in the country
The Thursday Murder Club: Launching a megabrand author - a publishing case study
No full textIn 2020, the Christmas book charts in the UK made headlines: Barack Obama’s eagerly awaited autobiography, The Promised Land, was beaten to the top spot by The Thursday Murder Club by Richard Osman, a debut cosy crime novel set in a retirement village. Not only did Osman’s book beat the former US president’s expected bestseller, it also broke records, becoming the fastest-selling debut crime novel of all time. Although Osman has a certain level of fame in the UK from his TV appearances on shows such as Pointless, his celebrity status does not entirely explain the novel’s huge sales. This article tracks the acquisition, publication, and promotion journey of The Thursday Murder Club in order to understand the industry and cultural context of its success and to interrogate the role of celebrity in the creation of author brands. The findings suggest that the unexpected scale of the success of the book owed to a number of factors, including in-depth editing by the novel’s agent, editor, and author to tighten up the plot, an extensive and strategic promotional campaign, the pandemic (which drove interest in the book’s genre and themes), and the quality of the writing. We find that the book’s success was accentuated by Osman’s celebrity status rather than being entirely reliant on it. This research adds to the growing scholarship on celebrity authorship by means of an in-depth case study and provides insight into the processes behind publishing a ‘celebrity’ book and launching a megabrand author
- …
