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
Publications

2023

Back to top