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.

Description in Czech
Cílem společného výzkumu je vyvinout technologie parametrizace s obohacováním řeči pro robustní automatické rozpoznávání řeči s velkým objemem trénovacích dat v rámci spolupráce mezi VUT a NTT. Práce je založena na nízkodimenzionálních reprezentacích dat (embeddings) produkovaných neuronovými sítěmi v různých místech řetězce zpracování.

Keywords
speech recognition, robustness, large data, DNN embeddings

Key words in Czech
rozpoznávání řeči, odolnost, velký objem dat,

English

Žmolíková Kateřina, Ing., Ph.D. - principal person responsible

Department of Computer Graphics and Multimedia
- responsible department (25.9.2017 - not assigned)
Speech Data Mining Research Group BUT Speech@FIT
- internal (25.9.2017 - 30.9.2018)
NTT Corporation
- client (25.9.2017 - 30.9.2018)
Research Centre of Information Technology
- co-beneficiary (25.9.2017 - 30.9.2018)
Department of Computer Graphics and Multimedia
- beneficiary (25.9.2017 - 30.9.2018)

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

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

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

ŽMOLÍKOVÁ, K. Summary report of project "Speech enhancement front-end for robust automatic speech recognition with large amount of training data" for Year 2017. Brno: NTT Corporation, 2017. 1 p.
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

Responsibility: Žmolíková Kateřina, Ing., Ph.D.