Foto von Ludwig Kürzinger

Dipl.-Ing. (Univ.) Ludwig Kürzinger

Technische Universität München

Lehrstuhl für Mensch - Maschine - Kommunikation (Prof. Rigoll)

Postadresse

Postal:
Theresienstr. 90
80333 München

Forschungsgebiete

• Sequence Classification
• Speech Recognition

  • Mittermaier, S.; Kürzinger, L.; Waschneck, B.; Rigoll.G.: Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions. 2019 mehr…
  • Kürzinger L., Watzel T., Li L., Baumgartner R., Rigoll G.: Exploring Hybrid CTC/Attention End-to-End Speech Recognition with Gaussian Processes. Proc. 21st International Conference on Speech and Computer SPECOM 2019, Springer, 2019Lecture Notes in Computer Science, pp. 258-269 mehr… Volltext ( DOI )
  • Watzel T., Li L., Kürzinger L., Rigoll G.: Deep Neural Network Quantizers Outperforming Continuous Speech Recognition Systems. Proc. 21st International Conference on Speech and Computer SPECOM 2019, Springer, 2019Lecture Notes in Computer Science, pp. 530-539 mehr… Volltext ( DOI )
  • Mandry, H.; Herkle, A.; L.; Kürzinger, L.; Müelich, S.; Becker, J.; Fischer, R.F.H.; Ortmanns, M.: Modular PUF Coding Chain with High-Speed Reed-Muller Decoder. International Symposium on Circuits and Systems, ISCAS 2019, 2019, pp. 1-5 mehr… Volltext ( DOI )

Lehre

Mensch-Maschine-Kommunikation I (WS 2019)

Studentische Arbeiten

Bei Anfragen zu studentischen Arbeiten reichen Sie bitte folgende Unterlagen mit ein:
• Aktueller Lebenslauf
• Notenauszug
• Bisherige Erfahrungen aus dem Themengebiet
• Starttermin

Offen

Alle ausgeschriebenen Arbeiten finden Sie hier.

Abgeschlossen

2019
• Performance and Robustness of Distilled Neural Networks for Hybrid Speech Recognition (Master's Thesis)
• Self-Attention-basierte Spracherkennung (Scientific Seminar)
• Generative Adversarial Networks for Hybrid Speech Recognition in Pytorch-kaldi (Research Internship)
• Adversarial Training for Robust Speech Recognition in Pytorch-kaldi (Research Internship)
• Adversial Training for Improving Robustness in Hybrid Speech Recognition (Master´s Thesis)
• Speech Recognition using GANs (Bachelor´s Thesis)
• Performance and Robustness of Distilled Neural Networks for hybrid Speech Recognition (Master´s Thesis)
• Varaiational Attention for End-to-End Speech Recognition (Master´s Thesis)
• A Lightweight Deep Learning Model For Keyword Spotting On Raw Audio Data (Master´s Thesis)
• End-to-end Speech Recognition with Attention-based Models for German (Interdisplinary Project)
• Speech Recognition with Vector Quantized Attention-based Encoders (Interdisplinary Project)
• Generative Adverasarial Networks for hybrid Speech Recognition (Research Internship)
• Adversarial Training for Robust Hybrid Speech Recognition (Research Internship)
• Self-Attention and the Transformer (Scientific Seminar)

2018
• Keyword Detection for Personal Speech-to-Text Assistants (Master´s Thesis)
• Evaluation of Recurrent Neural Networks with Connectionist Temporal Classification for End-to-End Approaches to Speech Recognition (Master´s Thesis)
• Exploration of Generative Neural Networks for Hybrid Speech Recognition (Master´s Thesis)
• Bag-of-Words Classification of Spoken Languages using Vector Quantizers (Master´s Thesis)
• Defensive Distillation (Scientific Seminar)
• Speech Recognition using Machine Learning on a GPU Server (Research Internship)
• Adversarial Deep Learning on Speech-To-Text (Interdisplinary Project)
• A Kaldi Speech Recognition Input Method (Interdisplinary Project)
• Visualization of Speech Data in the Kaldi Speech Recognition Toolkit (Research Internship)
• Visualization of Attention Activations in the ESPnet Speech Recognition Toolkit (Research Internship)
• Gaussian Process Hyperparameter Optimization (Research Internship)
• Variational Autoencoders and Vector-Quantizing Autoencoders for Speech Data (Research Internship)

2017
• Post-Quantum-secure Asymmetric Encryption with QC-MDPC Codes for mbedTLS (Interdisciplinary Project)
• Implementation and Evaluation of the Post-Quantum Secure GPT Encryption Scheme for Embedded Systems (Master´s Thesis)
• Post-Quantum-secure Autentification based on the Learning Parity Problem (Master´s Thesis)
• Survey and Hardware Implementation of McEliece-Type Post-quantum Cryptography (Master´s Thesis)

2016
• Optimierung eines auf Verkettung basierenden Decodieralgorithmus für RM-Codes (Bachelor´s Thesis)