Herr

Pavel Denisov

Doktorand
Institut für maschinelle Sprachverarbeitung
Digitale Phonetik

Kontakt

+49 711 685-81396

Pfaffenwaldring 5 b
70569 Stuttgart
Deutschland
Raum: 02.014

2019

  • P. Denisov and N. T. Vu. End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning. In Proceedings of Interspeech, 2019.
  • D. Ortega, C. Y. Li, G. Vallejo, P. Denisov, N. T. Vu. Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions. In Proceedings of the 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.
  • P. Denisov and N. T. Vu. IMS-Speech: A Speech to Text Tool. In Proceedings of the 30th Conference on Electronic Speech Signal Processing (ESSV), 2019.

2018

  • P. Denisov, N. T. Vu and M. Ferras. Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition. In Proceedings of the 13th ITG Conference on Speech Communication, 2018.

SS 2019 Spoken Language Processing

Since 08.2018:
PhD candidate in Digital Phonetics, Institut für Maschinelle Sprachverarbeitung, Universität Stuttgart

10.2017 - 07.2018:
Master Thesis Student, Working Student, Sony Stuttgart Technology Center

10.2016 - 07.2018:
MSc in Computational Linguistics, Institut für Maschinelle Sprachverarbeitung, Universität Stuttgart
Thesis: Transfer Learning for Robust Acoustic Modeling in Automatic Speech Recognition

11.2006 - 10.2016:
Software Engineer, Scoros International Inc.
Document Processing, Content Extraction, Release Engineering

09.2003 - 02.2009:
Diploma of Engineer, Saint Petersburg State University of Aerospace Instrumentation
Computer Aided Engineering

Zum Seitenanfang