RUS  ENG JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB
General information
Latest issue
Archive
Impact factor
Guidelines for authors

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



J. Sib. Fed. Univ. Math. Phys.:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


J. Sib. Fed. Univ. Math. Phys., 2015, Volume 8, Issue 2, Pages 208–216 (Mi jsfu423)  

Automated recognition of paralinguistic signals in spoken dialogue systems: ways of improvement

Maxim Sidorova, Alexander Schmitta, Eugene S. Semenkinb

a Institute of Communications Engineering, Ulm University, Albert Einstein-Allee, 43, Ulm, 89081, Germany
b Institute of Computer Science and Telecommunications, Siberian State Aerospace University, Krasnoyarskiy Rabochiy, 31, Krasnoyarsk, 660014, Russia

Abstract: The ability of artificial systems to recognize paralinguistic signals, such as emotions, depression, or openness, is useful in various applications. However, the performance of such recognizers is not yet perfect. In this study we consider several directions which can significantly improve the performance of such systems. Firstly, we propose building speaker- or gender-specific emotion models. Thus, an emotion recognition (ER) procedure is followed by a gender- or speaker-identifier. Speaker- or gender-specific information is used either for including into the feature vector directly, or for creating separate emotion recognition models for each gender or speaker. Secondly, a feature selection procedure is an important part of any classification problem; therefore, we proposed using a feature selection technique, based on a genetic algorithm or an information gain approach. Both methods result in higher performance than baseline methods without any feature selection algorithms. Finally, we suggest analysing not only audio signals, but also combined audio-visual cues. The early fusion method (or feature-based fusion) has been used in our investigations to combine different modalities into a multimodal approach. The results obtained show that the multimodal approach outperforms single modalities on the considered corpora. The suggested methods have been evaluated on a number of emotional databases of three languages (English, German and Japanese), in both acted and non-acted settings. The results of numerical experiments are also shown in the study.

Keywords: recognition of paralinguistic signals, machine learning algorithms, speaker-adaptive emotion recognition, multimodal approach.

Full text: PDF file (210 kB)
References: PDF file   HTML file
UDC: 519.87
Received: 19.01.2015
Received in revised form: 25.02.2015
Accepted: 20.03.2015
Language:

Citation: Maxim Sidorov, Alexander Schmitt, Eugene S. Semenkin, “Automated recognition of paralinguistic signals in spoken dialogue systems: ways of improvement”, J. Sib. Fed. Univ. Math. Phys., 8:2 (2015), 208–216

Citation in format AMSBIB
\Bibitem{SidSchSem15}
\by Maxim~Sidorov, Alexander~Schmitt, Eugene~S.~Semenkin
\paper Automated recognition of paralinguistic signals in spoken dialogue systems: ways of improvement
\jour J. Sib. Fed. Univ. Math. Phys.
\yr 2015
\vol 8
\issue 2
\pages 208--216
\mathnet{http://mi.mathnet.ru/jsfu423}


Linking options:
  • http://mi.mathnet.ru/eng/jsfu423
  • http://mi.mathnet.ru/eng/jsfu/v8/i2/p208

    SHARE: VKontakte.ru FaceBook Twitter Mail.ru Livejournal Memori.ru


    Citing articles on Google Scholar: Russian citations, English citations
    Related articles on Google Scholar: Russian articles, English articles
  • Журнал Сибирского федерального университета. Серия "Математика и физика"
    Number of views:
    This page:212
    Full text:46
    References:23

     
    Contact us:
     Terms of Use  Registration  Logotypes © Steklov Mathematical Institute RAS, 2020