A Novel Audio-Visual Natural Conversation Database
نویسندگان
چکیده
1 Abstract We present work in progress on creating and using a novel audiovisual database that contains a diverse set of conversational expressions. The database is currently undergoing cleaning, annotation and validation to make it useful for the research community. While our main focus is on conversational expressions, we believe that the audio data is of use for the language community. We aim to use the workshop to solicit collaboration from the vision and language community to further develop and exploit the database.
منابع مشابه
4D Cardiff Conversation Database (4D CCDb): a 4D database of natural, dyadic conversations
The 4D Cardiff Conversation Database (4D CCDb) is the first 4D (3D Video) audio-visual database containing natural conversations between pairs of people. This publicly available database contains 17 conversations which have been fully annotated for speaker and listener activity: conversational facial expressions, head motion, and verbal/non-verbal utterances. It can be accessed at http://www.cs...
متن کاملRobot as a multimodal human interface device
In this talk, we introduce a robot conversation system. Generally speaking, the conversation is not performed only through the exchange of speech information. It needs the exchange of visual information: facial expressions, body poses, and gestures convey rich information to achieve natural conversation. In this context, the body and the vision system of the robot, can be regard as the essentia...
متن کاملRunning head : Audio - visual speech perception is special Audio - visual speech perception is special
In face-to-face conversation speech is perceived by ear and eye. We studied the prerequisites of audio-visual speech perception by using perceptually ambiguous sine wave replicas of natural speech as auditory stimuli. When the subjects were not aware that the auditory stimuli were speech, they showed only negligible integration of auditory and visual stimuli. When the same subjects learned to p...
متن کاملHybrid Approach for Emotion Classification of Audio Conversation Based on Text and Speech Mining
One of the greatest challenges in speech technology is estimating the speaker’s emotion. Most of the existing approaches concentrate either on audio or text features. In this work, we propose a novel approach for emotion classification of audio conversation based on both speech and text. The novelty in this approach is in the choice of features and the generation of a single feature vector for ...
متن کاملL-Ball: Designing A Novel Sports Electronic Audio Ball for Visual Impairment Student
Background. A field study conducted by researchers found the balls used by visual impairment students at school basically used the sound by a small bell inside the ball. However, the sound emitted from the ball is very limited, the ball will sound when it is moved. This makes it difficult for students with visual impairments to find a missing ball that not emitted makes a sound. Objectives. A ...
متن کامل