Audio-visual Laughter Synthesis System
نویسندگان
چکیده
In this paper we propose an overview of a project aiming at building an audio-visual laughter synthesis system. The same approach is followed for acoustic and visual synthesis. First a database has been built to have synchronous audio and 3D visual landmarks tracking data. Then this data has been used to build HMM models of acoustic laughter and visual laughter separately. Visual laughter modeling was further separated into a facial modeling and head motion modeling. An automatic laughter segmentation process has been used to annotate visual laughter. Finally, simple rules were defined to synchronize all the different modalities to be able to produce new durations.
منابع مشابه
The AV-LASYN Database : A synchronous corpus of audio and 3D facial marker data for audio-visual laughter synthesis
A synchronous database of acoustic and 3D facial marker data was built for audio-visual laughter synthesis. Since the aim is to use this database for HMM-based modeling and synthesis, the amount of collected data from one given subject had to be maximized. The corpus contains 251 utterances of laughter from one male participant. Laughter was elicited with the help of humorous videos. The result...
متن کاملFinding out the audio and visual features that influence the perception of laughter intensity and differ in inhalation and exhalation phases
This paper presents the results of the analysis of laughter expressive behavior. First we present the intensity annotation study of an audiovisual corpus of spontaneous laughter. In the second part of the paper we present the analysis of audio and visual cues that influence the perception of laughter intensity, as well as the study of audio and visual features that differ in laughter inhalation...
متن کاملFusion for Audio-Visual Laughter Detection
Laughter is a highly variable signal, and can express a spectrum of emotions. This makes the automatic detection of laughter a challenging but interesting task. We perform automatic laughter detection using audio-visual data from the AMI Meeting Corpus. Audio-visual laughter detection is performed by combining (fusing) the results of a separate audio and video classifier on the decision level. ...
متن کاملLaughter modulation: from speech to speech-laugh
Laughing while speaking, also referred to as speech-laugh, occurs frequently in social conversations. In order to understand how laughter influences the acoustics of its co-occurring speech signal, we take a synthesis approach in designing an interactive system for artificial “laughter modulation”: users input an arbitrary speech signal, and the system processes the signal to yield acoustic pat...
متن کاملDecision-Level Fusion for Audio-Visual Laughter Detection
Laughter is a highly variable signal, which can be caused by a spectrum of emotions. This makes the automatic detection of laughter a challenging, but interesting task. We perform automatic laughter detection using audio-visual data from the AMI Meeting Corpus. Audiovisual laughter detection is performed by fusing the results of separate audio and video classifiers on the decision level. This r...
متن کامل