Please select the desired project time frame:

• July 2026
• January 2026
• July 2025
• January 2025
• July 2024
• January 2024
• July 2023
• January 2023
• July 2022
• January 2022
• July 2021
• January 2021
• July 2020
• January 2020
• July 2019
• January 2019
• July 2018
• January 2018
• July 2017
• January 2017
• July 2016
• January 2016
• July 2015
• January 2015
• July 2014
• January 2014
• July 2013
• January 2013
• July 2012
• January 2012
• July 2011
• January 2011
• July 2010
• January 2010
• July 2009
• January 2009
• July 2008
• January 2008
• July 2007
• January 2007
• July 2006
• January 2006
• July 2005
• January 2005
• July 2004
• January 2004
• July 2003
• January 2003
• July 2002
• January 2002
• July 2001
• January 2001

Start of funding 01.01.2009

Speaker identification and classification of speaker characteristics

---

The classification of speaker characteristics by a person's voice can be regarded as a classification task. The goal is to decide whether a speakers belongs to a specific speaker group. Speaker groups in this context are persons having specific characteristics in common like gender, age, country of birth, emotional state and so on. Even the identification of a speaker can be regarded as a classification of speaker groups, where the group contains exactly one person, i.e., the speaker himself. Thus, the classification of speaker characteristics can be achieved by means of speaker identification. The expected output of this project is the development of a generic system for the classification of speaker characteristics. The system will be evaluated on the two speaker characteristics age and language id / language of birth. The project will be concluded by a combination of the developed system with an existing speaker identification system.

Final report:
In the scope of the project, we developed syllable based constraints to select the most salient frames (of cepstral features) to train an acoustic speaker verification system [1]. The system was then integrated as a submodule in a complex speajer verification system, which combined feature-based and channel-based analysis methods to model intrinsic speaker variability for speaker verification [2].

[1] Bocklet, Tobias; Shriberg, Elizabeth. Speaker Recognition Using Syllable-Based Constraints for Cepstral Frame Selection.
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4525-4528, 2009, ISBN 978-1-4244-2354-5

[2] Graciarena, Martin; Bocklet, Tobias; Shriberg, Elizabeth; Stolcke, Andreas; Kajarekar, Sachin. Feature-Based and Channel-Based Analyses of Intrinsic Variability in Speaker Verification.
Proceedings of the 10th Annual Conference of the International Speech Communication Association (Interspeech 2009), vol. 1, pp. 2015-2018, 2009