Toward the Human Communication Efficiency Monitoring from Captured Audio and Video Media in Real Environments

Rutkowski, Tomasz M.; Seki, Syûzô; Yamakata, Yoko; Kakusho, Koh; Minoh, Michihiko

doi:10.1007/978-3-540-45226-3_149

Cited by 12 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Minoh and Kakusho developed a robust method for automatically recognizing communicative events in a real class room by integrating audio and visual information processing [14]. Rutkowski studied a method for monitoring and estimating efficiency of the human-human communication based on recorded audio and video by computing correlation between sender activities and receiver responses [15]. Taniguchi and Arita used computer vision techniques to realize the notion of real time human proxy to virtually create a classroom for distributed learning environments [16].…”

Section: Discussion and Future Perspectivesmentioning

confidence: 99%

Conversational Knowledge Process for Social Intelligence Design

Nishida

2004

Intelligence in Communication Systems

View full text Add to dashboard Cite

Abstract. The Internet and ubiquitous network technologies have succeeded in connecting people and knowledge over space and time. The next step is to realize knowledgeable communities on the ubiquitous network. Social Intelligence Design is a field of research on harmonizing people and artifacts by focusing on social intelligence, defined as the ability of actors and agents to learn and to solve problems as a function of social structure and to manage their relationships with each other. In this paper, I present a computational approach to understanding and augmenting the conversational knowledge process that is a collective activity for knowledge creation, management, and application where conversational communications are used as a primary means of interaction among participating agents. The key idea is conversation quantization, a technique of approximating a continuous flow of conversation by a series of conversation quanta that represent points of the discourse. Conversation quantization enables to implement a rather robust conversational system by basing it on a large amount of conversational quanta collected from the real world. I survey major results concerning acquisition, annotation, adaptation, and understanding of conversation quanta.

show abstract

Section: Discussion and Future Perspectivesmentioning

confidence: 99%

Conversational Knowledge Process for Social Intelligence Design

Nishida

2004

Intelligence in Communication Systems

View full text Add to dashboard Cite

show abstract

“…Minoh and Kakusho developed a robust method for automatically recognizing communicative events in a real class room by integrating audio and visual information processing [13]. Rutkowski studied a method for monitoring and estimating efficiency of the human-human communication based on recorded audio and video by computing correlation between sender activities and receiver responses [14]. Taniguchi and Arita used computer vision techniques to realize the notion of real time human proxy to virtually create a classroom for distributed learning environments [15].…”

Section: Future Workmentioning

confidence: 99%

Conversation Quantization for Conversational Knowledge Process

Nishida

2005

Databases in Networked Information Systems

View full text Add to dashboard Cite

Abstract. In this paper, I present a computational approach to understanding and augmenting the conversational knowledge process that is a collective activity for knowledge creation, management, and application where conversational communications are used as a primary means of interaction among participating agents. The key idea is conversation quantization, a technique of approximating a continuous flow of conversation by a series of conversation quanta that represent points of the discourse. Conversation quantization enables to implement a rather robust conversational system by basing it on a large amount of conversational quanta collected from the real world. I survey major results concerning capturing, accumulating, presenting, and understanding conversation quanta.

show abstract

“…where i ¼ 1; 2 and R A i , R V i , R A i V i stand for empirical estimates of the corresponding covariance matrices of the feature vectors [10] (computed recursively). Simultaneous activity estimates in the same modes (audio and video, respectively) are calculated for video and audio streams, respectively, as: Figure 6.…”

Section: Evaluation Of Communicative Interactivitymentioning

confidence: 99%

“…8). This synchronized audiovisual behavior of the sender and the unsynchronized one of the receiver characterizes an efficient communication [4,6,10].…”

mentioning

confidence: 99%

“…This is quantified by synchronization and interaction measures [4,6]. In [10] the communication efficiency is defined as a measure that characterizes the behavioral coordination of communicators. Here, a measure of the communication efficiency is proposed as a combination of four estimates of mutual information [11]: (1) two visual (V i ), (2) two audio (A i ), and (3) two pairs of audiovisual features (A i ; V i ).…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Multimodal Approach to Communicative Interactivity Classification

Rutkowski

Mandic

Barros

2007

J VLSI Sign Process Syst Sign Im

Self Cite

View full text Add to dashboard Cite

The problem of modality detection in so called communicative interactivity is addressed. Multiple audio and video recordings of human communication are analyzed within this framework, based on fusion of the extracted features. At the decision level, support vector machines (SVMs) are utilized to segregate between the communication modalities. The proposed approach is verified through simulations on real world recordings.

show abstract

Toward the Human Communication Efficiency Monitoring from Captured Audio and Video Media in Real Environments

Cited by 12 publications

References 2 publications

Conversational Knowledge Process for Social Intelligence Design

Conversational Knowledge Process for Social Intelligence Design

Conversation Quantization for Conversational Knowledge Process

A Multimodal Approach to Communicative Interactivity Classification

Contact Info

Product

Resources

About