Thilo von Neumann

32 papers A 5Misc 5Journal 17Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Error Analysis in a Modular Meeting Transcription System. CoRR Peter Vieting, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf Schlüter, Reinhold Haeb-Umbach
2024	—	`conf`	Combining TF-GridNet And Mixture Encoder For Continuous Speech Separation For Meeting Transcription. SLT Peter Vieting, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf Schlüter, Reinhold Haeb-Umbach
2024	—	`conf`	Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization. ICASSP Workshops Thilo von Neumann, Christoph Böddeker, Tobias Cord-Landwehr, Marc Delcroix, Reinhold Haeb-Umbach
2023	J	`jnl`	MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. CoRR Thilo von Neumann, Christoph Böddeker, Marc Delcroix, Reinhold Haeb-Umbach
2023	J	`jnl`	Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization. CoRR Thilo von Neumann, Christoph Böddeker, Tobias Cord-Landwehr, Marc Delcroix, Reinhold Haeb-Umbach
2023	J	`jnl`	Mixture Encoder Supporting Continuous Speech Separation for Meeting Recognition. CoRR Peter Vieting, Simon Berger, Thilo von Neumann, Christoph Böddeker, Ralf Schlüter, Reinhold Haeb-Umbach
2023	Misc	`conf`	On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems. ICASSP Thilo von Neumann, Christoph Böddeker, Keisuke Kinoshita, Marc Delcroix, Reinhold Haeb-Umbach
2023	J	`jnl`	Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria. IEEE ACM Trans. Audio Speech Lang. Process. Thilo von Neumann, Keisuke Kinoshita, Christoph Böddeker, Marc Delcroix, Reinhold Haeb-Umbach
2022	J	`jnl`	A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network. CoRR Tobias Gburrek, Christoph Böddeker, Thilo von Neumann, Tobias Cord-Landwehr, Joerg Schmalenstroeer, Reinhold Haeb-Umbach
2022	A	`conf`	An Initialization Scheme for Meeting Separation with Spatial Mixture Models. INTERSPEECH Christoph Böddeker, Tobias Cord-Landwehr, Thilo von Neumann, Reinhold Haeb-Umbach
2022	J	`jnl`	An Initialization Scheme for Meeting Separation with Spatial Mixture Models. CoRR Christoph Böddeker, Tobias Cord-Landwehr, Thilo von Neumann, Reinhold Haeb-Umbach
2022	—	`conf`	MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator. IWAENC Tobias Cord-Landwehr, Thilo von Neumann, Christoph Böddeker, Reinhold Haeb-Umbach
2022	—	`conf`	Monaural Source Separation: From Anechoic To Reverberant Environments. IWAENC Tobias Cord-Landwehr, Christoph Böddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2022	J	`jnl`	On Word Error Rate Definitions and their Efficient Computation for Multi-Speaker Speech Recognition Systems. CoRR Thilo von Neumann, Christoph Böddeker, Keisuke Kinoshita, Marc Delcroix, Reinhold Haeb-Umbach
2022	Misc	`conf`	SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. ICASSP Thilo von Neumann, Keisuke Kinoshita, Christoph Böddeker, Marc Delcroix, Reinhold Haeb-Umbach
2022	A	`conf`	Utterance-by-utterance overlap-aware neural diarization with Graph-PIT. INTERSPEECH Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix, Christoph Böddeker, Reinhold Haeb-Umbach
2022	J	`jnl`	Utterance-by-utterance overlap-aware neural diarization with Graph-PIT. CoRR Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix, Christoph Böddeker, Reinhold Haeb-Umbach
2021	A	`conf`	Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers. Interspeech Thilo von Neumann, Keisuke Kinoshita, Christoph Böddeker, Marc Delcroix, Reinhold Haeb-Umbach
2021	J	`jnl`	Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers. CoRR Thilo von Neumann, Keisuke Kinoshita, Christoph Böddeker, Marc Delcroix, Reinhold Haeb-Umbach
2021	J	`jnl`	Monaural source separation: From anechoic to reverberant environments. CoRR Tobias Cord-Landwehr, Christoph Böddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2021	J	`jnl`	SA-SDR: A novel loss function for separation of meeting style data. CoRR Thilo von Neumann, Keisuke Kinoshita, Christoph Böddeker, Marc Delcroix, Reinhold Haeb-Umbach
2021	—	`conf`	Speeding Up Permutation Invariant Training for Source Separation. ITG Conference on Speech Communication Thilo von Neumann, Christoph Böddeker, Keisuke Kinoshita, Marc Delcroix, Reinhold Haeb-Umbach
2021	J	`jnl`	Speeding Up Permutation Invariant Training for Source Separation. CoRR Thilo von Neumann, Christoph Böddeker, Keisuke Kinoshita, Marc Delcroix, Reinhold Haeb-Umbach
2020	Misc	`conf`	End-to-End Training of Time Domain Audio Separation and Recognition. ICASSP Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Böddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2020	A	`conf`	Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker Stream Separation. INTERSPEECH Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2020	A	`conf`	Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR. INTERSPEECH Thilo von Neumann, Christoph Böddeker, Lukas Drude, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2020	J	`jnl`	Multi-path RNN for hierarchical modeling of long sequential data and its application to speaker stream separation. CoRR Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2020	J	`jnl`	Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR. CoRR Thilo von Neumann, Christoph Böddeker, Lukas Drude, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2019	Misc	`conf`	All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis. ICASSP Thilo von Neumann, Keisuke Kinoshita, Marc Delcroix, Shoko Araki, Tomohiro Nakatani, Reinhold Haeb-Umbach
2019	J	`jnl`	All-neural online source separation, counting, and diarization for meeting analysis. CoRR Thilo von Neumann, Keisuke Kinoshita, Marc Delcroix, Shoko Araki, Tomohiro Nakatani, Reinhold Haeb-Umbach
2019	J	`jnl`	End-to-end training of time domain audio separation and recognition. CoRR Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Böddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2018	Misc	`conf`	Deep Attractor Networks for Speaker Re-Identification and Blind Source Separation. ICASSP Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach