Emotions are a personal thing: Towards speaker-adaptive emotion recognition

Sidorov, Maxim; Ultes, Stefan; Schmitt, Alexander

doi:10.1109/icassp.2014.6854514

Cited by 29 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, in order to extend the advantage of using the speaker-dependent classification-based emotion recognition [24,25] to regressionbased affect and depression recognition, a speaker identification approach has also been applied. The following subsections describe the process of SVM application for considering tasks more deeply.…”

Section: Emotion and Depression Predic-tion With Multimodal Featuresmentioning

confidence: 99%

“…In [5] the authors have achieved reasonable results in emotion recognition using the following set of audio-based features: the means, the standard deviations, the ranges, the maximum values, the minimum values and medians of the pitch and the energy. Regarding the learning stage of emotion recognition using audio cues, the most common algorithms used are Multi Layer Perceptron (MLP) [25] and Support Vector Machine (SVM) [12], as well as their combination [30].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Emotion Recognition and Depression Diagnosis by Acoustic and Visual Features

Sidorov

Minker

2014

Proceedings of the 4th International Workshop on Audio/Visual Emotion Challenge

Self Cite

View full text Add to dashboard Cite

There is an enormous number of potential applications of the system which is capable to recognize human emotions. Such opportunity can be useful in various applications, e.g., improvement of Spoken Dialogue Systems (SDSs) or monitoring agents in call-centers. Depression is another aspect of human beings which is closely related to emotions. The system, that can automatically diagnose patient's depression can be helpful to physicians in order to support their decisions and avoid critical mistakes. Therefore, the Affect and Depression Recognition Sub-Challenges (ASC and DSC correspondingly) of the second combined open Audio/Visual Emotion and Depression recognition Challenge (AVEC 2014) is focused on estimating emotions and depression. This study presents the results of multimodal affect and depression recognition based on four different segmentation methods, using support vector regression. Furthermore, a speaker identification procedure has been introduced in order to build the speaker-specific emotion/depression recognition systems.

show abstract

Section: Emotion and Depression Predic-tion With Multimodal Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Emotion Recognition and Depression Diagnosis by Acoustic and Visual Features

Sidorov

Minker

2014

Proceedings of the 4th International Workshop on Audio/Visual Emotion Challenge

Self Cite

View full text Add to dashboard Cite

show abstract

“…To overcoming the variability of the speaker, a novel speaker-independent emotional feature, a ratio of a spectral flatness measure to a spectral center, was suggested by Kim et al [7]. In 2015, Maxim Sidorov [8], [9] proposed a novel method on speech-based adaptive emotion recognition through addition of speaker specific information and achieved 10% accuracy improvement. And Iliou and Anagnostopoulos reported around a 51% recognition rate for seven emotions using neural networks [10].…”

Section: Introductionmentioning

confidence: 99%

Speaker-Independent Emotion Recognition for Interstate Measuring of User Based on Separation and Rejection

Kim¹,

Kim²

2018

IJMLC

View full text Add to dashboard Cite

The purpose of this paper is to develop a speakerindependent emotion recognition system for emotional interaction between humans and robots. Recognizing human emotion from speech is one of the challenges in the field of human-robot interaction. The ability to recognize emotions from an unspecified human, called speaker-independent emotion recognition, is important for commercial use in speech emotion recognition systems. However, generally, speakerindependent systems show lower performance compared with speaker-dependent systems, as emotional feature values depend on the speaker and his/her gender. Hence, this paper describes the realization of speaker-independent emotion recognition based on separation and rejection to make the emotion recognition system accurate and stable. Through comparison of the proposed methods with conventional method, the improvement and effectiveness of proposed methods were clearly confirmed.

show abstract

“…Busso et al [3] have achieved reasonable results in emotion recognition using the following set of audio-based features: the means, the standard deviations, the ranges, the maximum values, the minimum values and medians of the pitch and the energy. Regarding the learning stage of emotion recognition using audio cues, the most common algorithms applied are Multi Layer Perceptron (MLP) [22] and Support Vector Machine (SVM) [9], as well as their combination [25].…”

Section: Introductionmentioning

confidence: 99%

Automatic Recognition of Personality Traits

Sidorov

Ultes

Schmitt

2014

Proceedings of the 2014 Workshop on Mapping Personality Traits Challenge and Workshop

Self Cite

View full text Add to dashboard Cite

A system being capable of recognize personality traits may be utilized in an enormous number of applications. Adding personality-dependency may be useful to build speaker-adaptive models, e.g., to improve Spoken Dialogue Systems (SDSs) or to monitor agents in call-centers. Therefore, the First Audio/Visual Mapping Personality Traits Challenge (MAP-TRAITS 2014) focuses on estimating personality traits. In this context, this study presents the results for multimodal recognition of personality traits using support vector machines. As only small portions of the data is used for personality estimation at a time (which are later combined to a final estimate), different segmentation methods (and how to derive a final hypothesis) are analyzed regarding the task as both a regression and a classification problem.

show abstract

Emotions are a personal thing: Towards speaker-adaptive emotion recognition

Cited by 29 publications

References 8 publications

Emotion Recognition and Depression Diagnosis by Acoustic and Visual Features

Emotion Recognition and Depression Diagnosis by Acoustic and Visual Features

Speaker-Independent Emotion Recognition for Interstate Measuring of User Based on Separation and Rejection

Automatic Recognition of Personality Traits

Contact Info

Product

Resources

About