Project Details

NTT - Speech enhancement front-end for robust automatic speech recognition with large amount of training data

Project Period: 1. 10. 2017 – 30. 9. 2018

Project Type: contract

Partner: NTT Corporation

Czech title
NTT - Parametrizace s obohacováním řeči pro robustní automatické rozpoznávání řeči s velkým objemem trénovacích dat
Type
contract
Keywords

speech recognition, robustness, large data, DNN embeddings

Abstract

The purpose of the Joint Research is to develop Speech enhancement front-end for
robust automatic speech recognition with large amount of training data through
the cooperation of NTT and BUT. The work is relying on embeddings produced by
neural networks in various places of the processing chain.

Team members
Žmolíková Kateřina, Ing., Ph.D. (FIT) – research leader
Černocký Jan, prof. Dr. Ing. (DCGM)
Publications

2018

  • DELCROIX, M.; ŽMOLÍKOVÁ, K.; KINOSHITA, K.; ARAKI, S.; OGAWA, A.; NAKATANI, T. SpeakerBeam: A New Deep Learning Technology for Extracting Speech of a Target Speaker Based on the Speaker's Voice Characteristics. NTT Technical Review, 2018, vol. 16, no. 11, p. 19-24. ISSN: 1348-3447. Detail
  • DELCROIX, M.; ŽMOLÍKOVÁ, K.; KINOSHITA, K.; OGAWA, A.; NAKATANI, T. Single Channel Target Speaker Extraction and Recognition with Speaker Beam. In Proceedings of ICASSP 2018. Calgary: IEEE Signal Processing Society, 2018. p. 5554-5558. ISBN: 978-1-5386-4658-8. Detail
  • ROHDIN, J.; SILNOVA, A.; DIEZ SÁNCHEZ, M.; PLCHOT, O.; MATĚJKA, P.; BURGET, L. End-to-End DNN Based Speaker Recognition Inspired by i-Vector and PLDA. In Proceedings of ICASSP. Calgary: IEEE Signal Processing Society, 2018. p. 4874-4878. ISBN: 978-1-5386-4658-8. Detail

2017

  • ŽMOLÍKOVÁ, K. Souhrnná výzkumná zpráva projektu "Speech enhancement front-end for robust automatic speech recognition with large amount of training data" pro rok 2017. Brno: NTT Corporation, 2017. s. 0-0. Detail
  • ŽMOLÍKOVÁ, K.; DELCROIX, M.; KINOSHITA, K.; HIGUCHI, T.; OGAWA, A.; NAKATANI, T. Learning Speaker Representation for Neural Network Based Multichannel Speaker Extraction. In Proceedings of ASRU 2017. Okinawa: IEEE Signal Processing Society, 2017. p. 8-15. ISBN: 978-1-5090-4788-8. Detail
Back to top