Speaker characteristics and emotion classification

被引：10
作者：
Mustererkennung, Universität Erlangen-Nürnberg, Martensstr. 3, 91058 Erlangen, Germany [1 ]
不详 [2 ]
机构：
[1] Mustererkennung, Universität Erlangen-Nürnberg, 91058 Erlangen
[2] Sympalog Voice Solutions GmbH, 91052 Erlangen
来源：
Lect. Notes Comput. Sci. | 2007年 / 138-151期
关键词：
Acoustic features; Automatic classification; Emotion; Laryngealization; Speaker dependency; System architecture; Voice application;
D O I：
10.1007/978-3-540-74200-5_7
中图分类号：
学科分类号：
摘要：
In this paper, we address the -interrelated -problems of speaker characteristics (personalization) and suboptimal performance of emotion classification in state-of-the-art modules from two different points of view: first, we focus on a specific phenomenon (irregular phonation or laryngealization) and argue that its inherent multi-functionality and speaker-dependency makes its use as feature in emotion classification less promising than one might expect. Second, we focus on a specific application of emotion recognition in a voice portal and argue that constraints on time and budget often prevent the implementation of an optimal emotion recognition module. © Springer-Verlag Berlin Heidelberg 2007.
引用
收藏
页码：138 / 151
页数：13
相关论文
共 30 条
  • [21] Devillers L., Vidrascu L., Real-life Emotion Recognition in Speech, LNCS(LNAI, 4441, (2007)
  • [22] Batliner A., Buckow J., Huber R., Warnke V., Noth E., Niemann H., Prosodic Feature Evaluation: Brute Force or Well Designed?, Proc. of the 14th Int. Congress of Phonetic Sciences, 3, pp. 2315-2318, (1999)
  • [23] Batliner A., Buckow J., Huber R., Warnke V., Noth E., Niemann H., Boiling down Prosody for the Classification of Boundaries and Accents in German and English, Proc. 7th Eurospeech, pp. 2781-2784, (2001)
  • [24] Batliner A., Mobius B., Prosodic Models, Automatic Speech Understanding, and Speech Synthesis: Towards the Common Ground?, The Integration of Phonetic Knowledge in Speech Technology, pp. 21-44, (2005)
  • [25] Kochanski G., Grabe E., Coleman J., Rosner B., Loudness predicts Prominence
  • [26] Fundamental Frequency lends little, Journal of Acoustical Society of America, 11, pp. 1038-1054, (2005)
  • [27] Burkhardt F., van Ballegooy M., Englert R., Huber R., An emotion-aware voice portal, Proc. Electronic Speech Signal Processing ESSP, (2005)
  • [28] Huber R., Gallwitz F., Warnke V., Verbesserung eines Voiceportals mit Hilfe akustischer Klassifikation von Emotion, 34, pp. 577-581
  • [29] Batliner A., Burkhardt F., van Ballegooy M., Noth E., A Taxonomy of Applications that Utilize Emotional Awareness, Proceedings of IS-LTC, pp. 246-250, (2006)
  • [30] Burkhardt F., Huber R., Batliner A., Application of Speaker Classification in Human Machine Dialog Systems, LNCS(LNAI, 4343, (2007)
123