Foto von Lujun Li

Lujun Li, M.Eng.

Technische Universität München

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

Postadresse

Postal:
Arcisstr. 21
80333 München

Forschungsgebiete

• Deep Learning
• Speech Recognition Speech Recognition
• Speech Enhancement

 

Publikationen

  • Li, Lujun; Watzel, Tobias; Kuerzinger, Ludwig; Rigoll, Gerhard: Towards Constructing HMM Structure for Speech Recognition With Deep Neural Fenonic Baseform Growing. IEEE Access 9, 2021, 39098--39110 mehr… Volltext ( DOI )
  • Li, Lujun; Lu, Zhenxing; Watzel, Tobias; Kürzinger, Ludwig; Rigoll, Gerhard: Light-Weight Self-Attention Augmented Generative Adversarial Networks for Speech Enhancement. Electronics 10 (13), 2021, 1586 mehr… Volltext ( DOI )
  • Li, Lujun; Kang, Yikai; Shi, Yuchen; Kürzinger, Ludwig; Watzel, Tobias; Rigoll, Gerhard: Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition. arXiv preprint arXiv:2104.01471, 2021 mehr… Volltext ( DOI )
  • Watzel, Tobias; Kürzinger, Ludwig; Li, Lujun; Rigoll, Gerhard: Regularized Forward-Backward Decoder for Attention Models. 2020 mehr…
  • Kürzinger, Ludwig; Winkelbauer, Dominik; Li, Lujun; Watzel, Tobias; Rigoll, Gerhard: CTC-Segmentation of Large Corpora for German End-to-End Speech Recognition. Speech and Computer, Springer International Publishing, 2020 mehr…
  • Kürzinger, Ludwig; Chavez Rosas, Edgar Ricardo; Li, Lujun; Watzel, Tobias; Rigoll, Gerhard: Audio Adversarial Examples for Robust Hybrid CTC/Attention Speech Recognition. Speech and Computer, Springer International Publishing, 2020 mehr…
  • Watzel, Tobias; Kürzinger, Ludwig; Li, Lujun; Rigoll, Gerhard: Synchronized Forward-Backward Transformer for End-to-End Speech Recognition. Speech and Computer, Springer International Publishing, 2020 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 )

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

2020

• Deep Neural Fenonic Baseform Growing: A Novel Approach to Construct HMM Topologies for Speech Recognition (Masterarbeit-2020)
• A New Hybrid Framework Based on Hidden Markov Models and Deep Neural Network Vector Quantizer for Speech Recognition (Masterarbeit)
• The Implementation of SincNet in the Hybrid Speech Recognition Systems (Forschungspraxis-2020)
• A Method for the Construction of Acoustic Markov Models for Words (Research Internship)

2019

 

• Stochastic Adaptive Neural Architecture Search for Keyword Spotting (Scientific Seminar)
• Learning Transferable Architectures for Scalable Image Recognition (Scientific Seminar)

2018
• Attention Mechanism for Speech Recognition (Scientifc Seminar)