Project Details

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

Project Period: 2. 1. 2023 - 31. 1. 2024

Project Type: contract

Partner: NTT Corporation

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

speech recognition, speaker diarization, large data, robustness

Abstract

The joint research will aim at investigating and developing speech enhancement and speaker diarization techniques for automatic speech recognition systems that are trained using a large amount of training data.

Team members
Diez Sánchez Mireia, M.Sc., Ph.D. (UPGM FIT VUT) , research leader
Černocký Jan, prof. Dr. Ing. (UPGM FIT VUT) , team leader
Pavlus Ján, Ing. (UPGM FIT VUT)
Peng Junyi, Msc. Eng. (UPGM FIT VUT)
Švec Ján, Ing. (UPGM FIT VUT)
Publications

2023

  • DELCROIX Marc, TAWARA Naohiro, DIEZ Sánchez Mireia, LANDINI Federico Nicolás, SILNOVA Anna, OGAWA Atsunori, NAKATANI Tomohiro, BURGET Lukáš and ARAKI Shoko. Multi-Stream Extension of Variational Bayesian HMM Clustering (MS-VBx) for Combined End-to-End and Vector Clustering-based Diarization. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Dublin: International Speech Communication Association, 2023, pp. 3477-3481. ISSN 1990-9772. Detail
Back to top