Project Details

Robustní zpracování nahrávek pro operativu a bezpečnost

Project Period: 1. 10. 2020 - 30. 9. 2025

Project Type: grant

Code: VJ01010108

Agency: Ministry of Interior of the Czech Republic

Program: PROGRAM STRATEGICKÁ PODPORA ROZVOJE BEZPEČNOSTNÍHO VÝZKUMU ČR 2019-2025 (IMPAKT 1) PODPROGRAMU 1 SPOLEČNÉ VÝZKUMNÉ PROJEKTY (BV IMP1/1VS)

English title
Robust processing of recordings for operations and security
Type
grant
Keywords

speech recognition, robust, recordings, operations, security

Abstract

The aim of the project is to increase competencies, unification and greater coordination of two leading Czech research institutes, in the field of speech information mining from real recordings in the field of security and close cooperation with security corps to put research results into practice of investigation and intelligence. This goal includes a shift in robust automatic speech recognition (ASR), training / adaptation of ASRs for different environments, determining when a person is speaking in a recording (diarization), and researching recordings through acoustic queries (Query by Example)

Team members
Karafiát Martin, Ing., Ph.D. (UPGM FIT VUT) , research leader
Diez Sánchez Mireia, M.Sc., Ph.D. (UPGM FIT VUT) , team leader
Matějka Pavel, Ing., Ph.D. (UPGM FIT VUT) , team leader
Szőke Igor, Ing., Ph.D. (UPGM FIT VUT) , team leader
Malenovský Vladimír, Ing., Ph.D. (UPGM FIT VUT)
Mošner Ladislav, Ing. (UPGM FIT VUT)
Plchot Oldřich, Ing., Ph.D. (UPGM FIT VUT)
Schwarz Petr, Ing., Ph.D. (UPGM FIT VUT)
Publications

2021

  • LANDINI Federico Nicolás, GLEMBEK Ondřej, MATĚJKA Pavel, ROHDIN Johan A., BURGET Lukáš, DIEZ Sánchez Mireia and SILNOVA Anna. Analysis of the BUT Diarization System for Voxconverse Challenge. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021, pp. 5819-5823. ISBN 978-1-7281-7605-5. Detail
  • KARAFIÁT Martin, VESELÝ Karel, ČERNOCKÝ Jan, PROFANT Ján, NYTRA Jiří, HLAVÁČEK Miroslav and PAVLÍČEK Tomáš. Analysis of X-Vectors for Low-Resource Speech Recognition. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021, pp. 6998-7002. ISBN 978-1-7281-7605-5. Detail
Back to top