Thilo von Neumann

Nachrichtentechnik (NT) / Heinz Nixdorf Institut

Wissenschaftlicher Mitarbeiter

Forschung & Lehre

E-Mail:
vonneumann@nt.uni-paderborn.de
Telefon:
+49 5251 60-5288
Büro­anschrift:
Pohlweg 47-49
33098 Paderborn
Raum:
P7.2.06

Publikationen

Aktuelle Publikationen

Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization

T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, R. Haeb-Umbach, in: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE, 2024.

DOI PDF

Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria

T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023) 576–589.

DOI PDF

MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems

T. von Neumann, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.

PDF https://github.com/fgnt/meeteval

Multi-stage diarization refinement for the CHiME-7 DASR scenario

C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: 7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023), ISCA, 2023.

DOI

On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems

T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, R. Haeb-Umbach, in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023.

DOI PDF https://github.com/fgnt/meeteval

Alle Publikationen anzeigen