Reinhold Haeb‐Umbach

Paderborn University — Germany

Computer Science · Physical Sciences

39h-index7.7kcitations391works2.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech and Audio Processing(272), Speech Recognition and Synthesis(216), Music and Audio Processing(142), Advanced Adaptive Filtering Techniques(68), Blind Source Separation Techniques(45)

Publications391 total

Error Analysis in a Modular Meeting Transcription System
arXiv (Cornell University)·2025Open Access
Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice
2025Open Access
Spatio-Spectral Diarization of Meetings by Combining TDOA-based Segmentation and Speaker Embedding-based Clustering
2025· 1 citedOpen Access
Towards Frame-level Quality Predictions of Synthetic Speech
2025· 1 citedOpen Access
Speech Synthesis along Perceptual Voice Quality Dimensions
2025
Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models
2025
30+ Years of Source Separation Research: Achievements and Future Challenges
2025· 7 cited
30+ Years of Source Separation Research: Achievements and Future Challenges
arXiv (Cornell University)·2025Open Access
Speech Synthesis along Perceptual Voice Quality Dimensions
arXiv (Cornell University)·2025Open Access
Word Error Rate Definitions and Algorithms for Long-Form Multi-Talker Speech Recognition
IEEE Transactions on Audio Speech and Language Processing·2025· 1 citedOpen Access
Combining TF-GridNet And Mixture Encoder For Continuous Speech Separation For Meeting Transcription
2024· 1 cited
Microphone Array Signal Processing and Deep Learning for Speech Enhancement: Combining model-based and data-driven approaches to parameter estimation and filtering
IEEE Signal Processing Magazine·2024· 5 citedOpen Access
Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models
arXiv (Cornell University)·2024Open Access
Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models
2024· 1 cited
Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder
VBN Forskningsportal (Aalborg Universitet)·2024Open Access
Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment
2024· 3 citedOpen Access
Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models
arXiv (Cornell University)·2024Open Access
Target-Specific Dataset Pruning for Compression of Audio Tagging Models
2024· 3 cited
Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder
2024
Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment
arXiv (Cornell University)·2024Open Access
page 1 of 20Next →

Frequent Co-authors

Lukas Drude(19), Jahn Heymann(13), Tomohiro Nakatani(9), Christoph Boeddeker(9), Hermann Ney(8), Keisuke Kinoshita(7), Marc Delcroix(7), Bhiksha Raj(4), Joerg Schmalenstroeer(4), Takuya Yoshioka(3), Ernst Warsitz(3), Shinji Watanabe(3), Jens Heitkaemper(3), Alexander Krueger(3), Xavier Aubert(3), Jinyu Li(2), Li Deng(2), Emanuël A. P. Habets(2), Volker Leutnant(2), Armin Sehr(2)