direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Dr. Tim Polzehl

Crowdsourcing Technology

  • High-quality data collection via crowdsourcing
  • Data management and data services via crowdsourcing (clean, index, verify, tag, label, translate, summarize, join, etc. )
  • Data synthesis und data generation via crowdsourcing
  • Subjective influences and bias normalization in crowdsourcing
  • Crowd-creation, crowd-voting, crowd-storming, crowd-testing applications
  • Crowdsourcing service for machine learning and BI
  • Crowdsourcing business and Business Logic
  • Complex automated workflows: combining human and artificial intelligence
  • Crowdsourcing with mobile devices
  • Real-time crowdsourcing
  • Skill-based crowdsourcing and verification of crowd-experts


Speech Technology

  • Automatic user classification
  • Automatic speaker characterization (age, gender, emotion, personality) 
  • Automatic speech recognition (ASR),
  • Prosody and voice gesture recognition
  • Prosodic voice print analysis, phonetic science
  • App development with speech functionalities (Android, iOS)


Text Classification, Natural Language Processing (NLP)  

  • Sentiment Analysis
  • Affective Analysis, Emotion
  • Personality und Lifestyle Detection from Social-Networks (Twitter, FB, G+, etc.)


Machine Learning and Artificial Intelligence  

  • Automated user modelling
  • Classification and prediction systems using linear and non-linear algorithms
  • Feature selection and reduction
  • Evaluation and verification methods


Running and Past Projects:

please click here.



Project Biography 

Tim Polzehl studied Science of Communication at Berlin's Technical University. Combining linguistic knowledge with signal processing skills he focused on speech interpretation and automatic data- and metadata extraction. He gathered experience within the field of machine learning as exercised when recognizing human speech utterances and classifying emotional expression subliminal in speech, the latter of which became his M.A. thesis. 

In 2008 Tim Polzehl started his position as PhD candidate in Telekom Innovation Laboratories (T-Labs) and the Quality and Usability Lab. He worked in both industrial and academic projects with focus on speech technology, App-Development, machine learning crowd sourcing solutions.

2011-2013 Tim was leading a R&D Project for Telekom Innovation Laboratories with Applications in the field of Intelligent Customer-Care Systems and Speech-Apps [1].

2012-2014 Tim was awarded with an BMBF funded Education program for future IT and Development Leadership involving SAP, Software AG, Scheer Group, Siemens, Holtzbrinck, Bosch, Datev and Deutsche Telekom AG, amongst highly ranked academic institution (Softwarecampus [2]).       

2014 Tim was awarded the PhD for his work on automatic prediction of personality attributes from speech.

Since 2014 Tim has been working as a Postdoc at the Quality and Usability chair of TU-Berlin. At the same time Tim is driving the start-up activity applying the earlier  development of crowdsourcing solutions Crowdee [3].



Quality and Usability Labs

Technische Universität Berlin

Ernst-Reuter-Platz 7

D-10587 Berlin

Tel.:+49 (30) 8353-58227Fax: +49 (30) 8353-58409mailto:tim.polzehl@qu.tu-berlin.de [4]

Openings / Supervision

please refer to here [5].


next >> [9]

Metze, F. and Polzehl, Tim and Black, Alan (2011). A Review of Personality in Voice-Based Man Machine Interaction [13]. Human-Computer Interaction. Interaction Techniques and Environments - 14th International Conference, HCI International 2011. Springer, 358–367.

Bhargava, Mayank and Polzehl, Tim (2013). Improving Automatic Emotion Recognition from speech using Rhythm and Temporal feature [14]. ICECIT. Elsevier.

Link to original publication [15]

Iskender, Neslihan and Gabryszak, Aleksandra and Polzehl, Tim and Hennig, Leonhard and Möller, Sebastian (2019). A Crowdsourcing Approach to Evaluate the Quality of Query-based Extractive Text Summaries [16]. 2019 Eleventh International Conference on Quality of Multimedia Experience (QoMEX). IEEE, 1–3.

Link to publication [17]

Möller, Sebastian and Hinterleitner, Florian and Lewcio, Blazej and Polzehl, Tim (2011). Speech Quality Measurement and Prediction: NGMNs, TTS and Personality [18]. Workshop Quality Perception in Conversational and Synthetic Speech

Möller, Sebastian and Wechsung, Ina and Kühnel, Christine and Polzehl, Tim and Schultz, Tanja and Putze, Felix (2011). Evaluation of Cognitive Interactive Systems: Problem Formulation and First Insights. Invited talk, Workshop on Benchmarking and Evaluation of Interactive Cognitive Systems (BCogS 2011) [19].

Naderi, Babak and Polzehl, Tim and Wechsung, Ina and Köster, Friedemann and Möller, Sebastian (2015). Effect of Trapping Questions on the Reliability of Speech Quality Judgments in a Crowdsourcing Paradigm [20]. 16th Ann. Conf. of the Int. Speech Comm. Assoc. (Interspeech 2015). ISCA, 2799–2803.

Link to publication [21] Link to original publication [22]

Polzehl, Tim and Möller, Sebastian and Metze, Florian (2011). Modeling Speaker Personality using Voice [23]. Proc. 12th Ann. Conf. of the Int. Speech Communication Assoc. (Interspeech 2011). International Speech Communication Association (ISCA).

Link to publication [24]

Polzehl, Tim and Naderi, Babak and Köster, Friedemann and Möller, Sebastian (2015). Robustness in Speech Quality Assessment and Temporal Training Expiry in Mobile Crowdsourcing Environments [25]. 16th Ann. Conf. of the Int. Speech Comm. Assoc. (Interspeech 2015). ISCA, 2794–2798.

Link to publication [26] Link to original publication [27]

Polzehl, Tim and Metze, Florian (2008). Using prosodic features to prioritize voice messages [28].

Iskender, Neslihan and Polzehl, Tim and Möller, Sebastian (2020). Crowdsourcing versus the laboratory: towards crowd-based linguistic text quality assessment of query-based extractive summarization [29]. Proceedings of the Conference on Digital Curation Technologies (Qurator 2020). CEUR, 1–16.

Link to publication [30] Link to original publication [31]

Iskender, Neslihan and Polzehl, Tim and Möller, Sebastian (2020). Towards a Reliable and Robust Methodology for Crowd-Based Subjective Quality Assessment of Query-Based Extractive Text Summarization [32]. Proceedings of The 12th Language Resources and Evaluation Conference. European Language Resources Association (ELRA), 245–253.

Link to publication [33] Link to original publication [34]

Hinterleitner, Florian and Möller, Sebastian and Polzehl, Tim and Falk, Tiago H. (2010). Comparison of Approaches for Instrumentally Predicting the Quality of Text-to-Speech Systems: Data from Blizzard Challenges 2008 and 2009 [35]. Proceedings of the Blizzard Challenge Workshop. International Speech Communication Association (ISCA), 1–7.

Link to publication [36]

Iskender, Neslihan and Polzehl, Tim and Möller, Sebastian (2020). Best Practices for Crowd-based Evaluation of German Summarization: Comparing Crowd, Expert and Automatic Evaluation [37]. Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems. Association for Computational Linguistics (ACL), 164–175.

Link to publication [38] Link to original publication [39]

Köster, Friedemann and Mittag, Gabriel and Polzehl, Tim and Möller, Sebastian (2016). Non-intrusive Estimation of Noisiness as a Perceptual Quality Dimension of Transmitted Speech [40]. 5th ISCA/DEGA Workshop on Perceptual Quality of Systems (PQS 2016). ISCA/DEGA, 74–78.

Link to publication [41]

Metze, F. and Batliner, A. and Eyben, F. and Polzehl, Tim and Schuller, B. and Steidl, S. (2010). Emotion Recognition using Imperfect Speech Recognition [42]. Proc. of the Annual Conference of the International Speech Communication Association (Interspeech 2009). IEEE, 1–6.

next >> [46]
------ Links: ------

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Copyright TU Berlin 2008