Towards Emotion, Age- and Gender-Aware VoiceXML Applications

被引：0

作者：

Schmitt, Alexander ^{[1
]}

Heinroth, Tobias ^{[1
]}

Bertrand, Gregor ^{[1
]}

机构：

[1] Univ Ulm, Inst Informat Technol, D-89069 Ulm, Germany

来源：

INTELLIGENT ENVIRONMENTS 2009 | 2009年 / 2卷

关键词：

Gender Classification; Emotion Recognition; Speaker Age; VoiceXML; system architecture;

D O I：

10.3233/978-1-60750-034-6-34

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a speaker classification architecture for VoiceXML-based applications. Our analysis component receives user utterances from the VoiceXML platform, performs feature extraction and classifies speaker characteristics such as age, gender and emotional state. This additional information about the speaker can be employed to adapt system prompts and the dialogue strategy to specific user groups. The implementation of our prototype shows, that speaker classification is feasible without significant delays and with high accuracies of over 95% for anger detection and gender classification.

引用

页码：34 / 41

页数：8

共 14 条

[1] Speaker characteristics and emotion classification [J].

Mustererkennung, Universität Erlangen-Nürnberg, Martensstr. 3, 91058 Erlangen, Germany ;

不详 .

Lect. Notes Comput. Sci., 2007, (138-151) :138-151

[2]

Boersma P., 2021, Glot International, DOI DOI 10.1097/AUD.0B013E31821473F7

[3]

Burkhardt F., 2007, SPEAKER CLASSIFICATI, P174

[4]

Burkhardt F., 2005, P INTERSPEECH, DOI DOI 10.21437/INTERSPEECH.2005-446

[5]

BURKHARDT F, 2007, ADV DIGITAL SPEECH T, pCH17

[6]

*DAT, 2007, UND KEY DRIV IVR INV

[7]

HERM O, 2008, P INT C SPEECH LANG

[8]

LEONARD RG, 1984, INT C AC SPEECH SIGN

[9]

METZE F, 2008, UNIVERSAL ACCESS INF, V8

[10]

Metze Florian, 2007, P INT C AC SPEECH SI, V1

← 1 2 →