Bimodal classification of English allophones employing acoustic speech signal and facial motion capture

2018 ◽  
Vol 144 (3) ◽  
pp. 1801-1802
Author(s):  
Andrzej Czyzewski ◽  
Szymon Zaporowski ◽  
Bozena Kostek
Keyword(s):  
Motion Capture ◽  
Speech Signal ◽  
Facial Motion ◽  
Acoustic Speech Signal

scholarly journals Vitality Forms Analysis and Automatic Recognition

2021 ◽  
Author(s):  
Radoslaw Niewiadomski ◽  
Amrita Suresh ◽  
Alessandra Sciutti ◽  
Giuseppe DI Cesare
Keyword(s):  
Motion Capture ◽  
Automatic Classification ◽  
Automatic Recognition ◽  
Motion Capture Data ◽  
Spatiotemporal Characteristics ◽  
The Way

The form of an action, i.e. the way it is performed, conveys important information about the performer’s attitude. In this paper we investigate spatiotemporal characteristics of different gestures performed with specific vitality forms and we study whether it is possible to recognize these aspects of action automatically. As the first step, we created a new dataset of 7 gestures performed with a vitality form (gentle and rude) or without a vitality form (neutral, slow and fast). Thousand repetitions were collected from 2 professional actors. Next, we identified 22 features from the motion capture data. According to the results, vitality forms are not merely characterized by a velocity/acceleration modulation but by a combination of different spatiotemporal properties. We also perform automatic classification of vitality forms with F-score of 87.3%.

Speech Recognition Using Combined Fuzzy and Ant Colony algorithm

2016 ◽  
Vol 6 (5) ◽  
pp. 2205
Author(s):  
Fooad Jalili ◽  
Milad Jafari Barani
Keyword(s):  
Speech Recognition ◽  
Dimensionality Reduction ◽  
Input Signal ◽  
Speech Signal ◽  
Fuzzy System ◽  
Ant Colony Algorithm ◽  
Noise Removal ◽  
Ant Colony ◽  
Speech Detection

<p><span>In recent years various methods has been proposed for speech recognition and removing noise from the speech signal became an important issue. In this paper a fuzzy system has been proposed for speech recognition that can obtain accurate results using classification of speech signals with “Ant Colony” algorithm.  First, speech samples are given to the fuzzy system to obtain a pattern for every set of signals that can be helpful for dimensionality reduction, easier checking of outcome and better recognition of signals.  Then, the “ACO” algorithm is used to cluster these signals and determine a cluster for each input signal. Also, with this method we will be able to recognize noise and consider it in a separate cluster and remove it from the input signal. Results show that the accuracy for speech detection and noise removal is desirable.</span></p>

Sign in / Sign up

Export Citation Format

Share Document