Deep learning for human affect recognition: Insights and new developments
Automatic human affect recognition is a key step towards more natural human-computer
interaction. Recent trends include recognition in the wild using a fusion of audiovisual and …
interaction. Recent trends include recognition in the wild using a fusion of audiovisual and …
Cross-language acoustic emotion recognition: An overview and some tendencies
SM Feraru, D Schuller - 2015 International Conference on …, 2015 - ieeexplore.ieee.org
Automatic emotion recognition from speech has matured close to the point where it reaches
broader commercial interest. One of the last major limiting factors is the ability to deal with …
broader commercial interest. One of the last major limiting factors is the ability to deal with …
Developing a benchmark for emotional analysis of music
Music emotion recognition (MER) field rapidly expanded in the last decade. Many new
methods and new audio features are developed to improve the performance of MER …
methods and new audio features are developed to improve the performance of MER …
Knowledge transfer from weakly labeled audio using convolutional neural network for sound events and scenes
A Kumar, M Khadkevich… - 2018 IEEE International …, 2018 - ieeexplore.ieee.org
In this work we propose approaches to effectively transfer knowledge from weakly labeled
web audio data. We first describe a convolutional neural network (CNN) based framework …
web audio data. We first describe a convolutional neural network (CNN) based framework …
[PDF][PDF] The INTERSPEECH 2015 computational paralinguistics challenge: Nativeness, Parkinson's & eating condition
Abstract The INTERSPEECH 2015 Computational Paralinguistics Challenge addresses
three different problems for the first time in research competition under well-defined …
three different problems for the first time in research competition under well-defined …
Application of LSTM networks for water demand prediction in optimal pump control
C Kühnert, NM Gonuguntla, H Krieg, D Nowak… - Water, 2021 - mdpi.com
Every morning, water suppliers need to define their pump schedules for the next 24 h for
drinking water production. Plans must be designed in such a way that drinking water is …
drinking water production. Plans must be designed in such a way that drinking water is …
Cross-corpus acoustic emotion recognition with multi-task learning: Seeking common ground while preserving differences
There is growing interest in emotion recognition due to its potential in many applications.
However, a pervasive challenge is the presence of data variability caused by factors such as …
However, a pervasive challenge is the presence of data variability caused by factors such as …
New approach in quantification of emotional intensity from the speech signal: emotional temperature
The automatic speech emotion recognition has a huge potential in applications of fields
such as psychology, psychiatry and the affective computing technology. The spontaneous …
such as psychology, psychiatry and the affective computing technology. The spontaneous …
Bird species identification via transfer learning from music genres
S Ntalampiras - Ecological informatics, 2018 - Elsevier
Humans possess the ability to apply previously acquired knowledge to deal with novel
problems quite efficiently. Transfer Learning is inspired by exactly that ability and has been …
problems quite efficiently. Transfer Learning is inspired by exactly that ability and has been …
Shared acoustic codes underlie emotional communication in music and speech—Evidence from deep transfer learning
E Coutinho, B Schuller - PloS one, 2017 - journals.plos.org
Music and speech exhibit striking similarities in the communication of emotions in the
acoustic domain, in such a way that the communication of specific emotions is achieved, at …
acoustic domain, in such a way that the communication of specific emotions is achieved, at …