45 citations · 154 across the 18 of their papers we have counts for
18 papers
Speech Quality-Based Localization of Low-Quality Speech and Text-to-Speech Synthesis Artefacts
Michael Kuhlmann, Alexander Werning, Thilo von Neumann +1
A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cann…
On the Role of Spatial Features in Foundation-Model-Based Speaker Diarization
Marc Deegen, Tobias Gburrek, Tobias Cord-Landwehr +4
Recent advances in speaker diarization exploit large pretrained foundation models, such as WavLM, to achieve state-of-the-art performance on multiple datasets. Systems like DiariZe…
Error Analysis in a Modular Meeting Transcription System
Peter Vieting, Simon Berger, Thilo von Neumann +3
Meeting transcription is a field of high relevance and remarkable progress in recent years. Still, challenges remain that limit its performance. In this work, we extend a previousl…
Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization
Thilo von Neumann, Christoph Boeddeker, Tobias Cord-Landwehr +2
We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset. Using a Continuo…
Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription
Peter Vieting, Simon Berger, Thilo von Neumann +3
Many real-life applications of automatic speech recognition (ASR) require processing of overlapped speech. A common method involves first separating the speech into overlap-free st…
MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems
Thilo von Neumann, Christoph Boeddeker, Marc Delcroix +1
MeetEval is an open-source toolkit to evaluate all kinds of meeting transcription systems. It provides a unified interface for the computation of commonly used Word Error Rates (WE…
On Word Error Rate Definitions and their Efficient Computation for Multi-Speaker Speech Recognition Systems
Thilo von Neumann, Christoph Boeddeker, Keisuke Kinoshita +2
We propose a general framework to compute the word error rate (WER) of ASR systems that process recordings containing multiple speakers at their input and that produce multiple out…
MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator
Tobias Cord-Landwehr, Thilo von Neumann, Christoph Boeddeker +1
The scope of speech enhancement has changed from a monolithic view of single, independent tasks, to a joint processing of complex conversational speech recordings. Training and eva…
Utterance-by-utterance overlap-aware neural diarization with Graph-PIT
Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix +2
Recent speaker diarization studies showed that integration of end-to-end neural diarization (EEND) and clustering-based diarization is a promising approach for achieving state-of-t…
A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network
Tobias Gburrek, Christoph Boeddeker, Thilo von Neumann +3
We propose a system that transcribes the conversation of a typical meeting scenario that is captured by a set of initially unsynchronized microphone arrays at unknown positions. It…
An Initialization Scheme for Meeting Separation with Spatial Mixture Models
Christoph Boeddeker, Tobias Cord-Landwehr, Thilo von Neumann +1
Spatial mixture model (SMM) supported acoustic beamforming has been extensively used for the separation of simultaneously active speakers. However, it has hardly been considered fo…
Monaural source separation: From anechoic to reverberant environments
Tobias Cord-Landwehr, Christoph Boeddeker, Thilo von Neumann +3
Impressive progress in neural network-based single-channel speech source separation has been made in recent years. But those improvements have been mostly reported on anechoic data…
SA-SDR: A novel loss function for separation of meeting style data
Thilo von Neumann, Keisuke Kinoshita, Christoph Boeddeker +2
Many state-of-the-art neural network-based source separation systems use the averaged Signal-to-Distortion Ratio (SDR) as a training objective function. The basic SDR is, however,…
Speeding Up Permutation Invariant Training for Source Separation
Thilo von Neumann, Christoph Boeddeker, Keisuke Kinoshita +2
Permutation invariant training (PIT) is a widely used training criterion for neural network-based source separation, used for both utterance-level separation with utterance-level P…
Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers
Thilo von Neumann, Keisuke Kinoshita, Christoph Boeddeker +2
Automatic transcription of meetings requires handling of overlapped speech, which calls for continuous speech separation (CSS) systems. The uPIT criterion was proposed for utteranc…
Multi-path RNN for hierarchical modeling of long sequential data and its application to speaker stream separation
Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix +2
Recently, the source separation performance was greatly improved by time-domain audio source separation based on dual-path recurrent neural network (DPRNN). DPRNN is a simple but e…
Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
Thilo von Neumann, Christoph Boeddeker, Lukas Drude +4
Most approaches to multi-talker overlapped speech separation and recognition assume that the number of simultaneously active speakers is given, but in realistic situations, it is t…
End-to-end training of time domain audio separation and recognition
Thilo von Neumann, Keisuke Kinoshita, Lukas Drude +4
The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition. However, up until now,…